{"adoption": {"forks": 107, "observed_at": "2026-08-28T04:04:08.691054+00:00", "stars": 1254}, "canonical_url": "https://ross.abutalabs.com/products/llm-transparency-tool", "card": {"archived": true, "artifact_type": "application", "description": "LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo", "domain": ["large-language-models", "machine-learning", "deep-learning", "data-visualization"], "enriched": true, "function": ["machine-learning", "llm-inference", "data-visualization", "developer-tools"], "health_score": 10, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["facebookresearch/llm-transparency-tool"], "name": "facebookresearch/llm-transparency-tool", "platform": ["python", "cross-platform"], "pushed_at": "2024-12-03T22:41:46+00:00", "repo": "facebookresearch/llm-transparency-tool", "stars": 1254, "tags": ["interpretability", "transformer-lens", "streamlit", "attention-analysis", "contribution-graph", "explainability", "research-tool", "research", "docker", "web-server"], "topics": [], "urls": [], "use_cases": ["inspect how a transformer LLM processes a prompt internally", "visualize token contribution graphs for model interpretability", "see which attention heads promote or suppress output tokens", "debug why an LLM made a certain prediction", "analyze FFN neuron activations in a language model", "research tool for mechanistic interpretability of transformers"], "what_it_is": "An interactive toolkit from Meta Research for analyzing the internal workings of Transformer-based language models. It visualizes contribution graphs of tokens, attention heads, and FFN neurons through a Streamlit web UI to explain model predictions.", "when_to_avoid": ["you need production LLM serving or inference at scale", "your model isn't supported by TransformerLens and you can't implement a custom TransparentLlm wrapper", "you need automated interpretability pipelines rather than interactive exploration"], "when_to_choose": ["you need interactive, visual interpretability analysis of a TransformerLens-supported model", "you're doing research on how LLMs make predictions", "you want to inspect attention heads and FFN contributions per token"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-transparency-tool", "repo": "facebookresearch/llm-transparency-tool", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.691054+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:07:23.961383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "764c71408b3ec25e3fc8ea6adb6e5b92493a7f35fbfa08b8ac988146b2887b3c", "fetched_at": "2026-08-28T04:04:08.691054+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/llm-transparency-tool"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 70, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 986, "days_push": 638, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}