# JShollaj/awesome-llm-interpretability

A curated list of Large Language Model (LLM) Interpretability resources.

Repository: https://github.com/JShollaj/awesome-llm-interpretability
Canonical: https://ross.abutalabs.com/products/awesome-llm-interpretability
License Family: other
Topics: awesome, awesome-list
Last push: 2026-08-11T01:22:02+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 70
- inputs: {"age_days": 984, "days_push": 23, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1644, forks 118 (observed 2026-08-28T04:05:16.024735+00:00)

## What it is
A curated awesome-list of Large Language Model (LLM) interpretability resources, including tools, papers, articles, and research communities. It serves as a reference index rather than a runnable software artifact.

## Use cases
- find tools for interpreting LLM behavior
- discover papers on mechanistic interpretability
- learn how to analyze transformer attention and neurons
- find communities researching AI interpretability
- locate sparse autoencoder and activation analysis resources
- get started with LLM explainability research

## When to choose
- you want a curated starting point for LLM interpretability research
- you need to discover tools, papers, and communities in one place
- you are exploring explainability and mechanistic interpretability for transformers

## When to avoid
- you need a runnable library or tool rather than a resource list
- you need production interpretability features out of the box
- you need guaranteed maintenance or licensing since it is just a curated list

## Facets
- artifact type: learning-resource
- maturity: active
- function: developer-tools
- domain: large-language-models, machine-learning, awesome-lists, tutorials
- platform: cross-platform
- tags: awesome-list, interpretability, mechanistic-interpretability, explainability, curated-resources

## Member repositories
- JShollaj/awesome-llm-interpretability (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.024735+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:45:47.807778+00:00, confidence not recorded.
  - readme: https://github.com/JShollaj/awesome-llm-interpretability (fetched 2026-08-28T04:05:16.024735+00:00, sha a7ebd5f105be)
- Data as of 2026-08-30T08:39:29.467469+00:00.