Skip to content
@goodfire-ai

Goodfire

Understanding and intentionally designing the next frontier of safe and powerful AI systems.

Popular repositories Loading

  1. r1-interpretability r1-interpretability Public

    Open source interpretability artefacts for R1.

    Jupyter Notebook 183 11

  2. param-decomp param-decomp Public

    Parameter Decomposition

    Python 142 54

  3. causalab causalab Public

    Python 114 39

  4. scribe scribe Public

    Python 87 17

  5. goodfire-sdk goodfire-sdk Public archive

    Ember is a hosted API/SDK that lets you shape AI model behavior by directly controlling a model's internal units of computation, or "features". With Ember, you can modify features to precisely cont…

    Python 55 14

  6. sdxl-turbo-interpretability sdxl-turbo-interpretability Public

    Jupyter Notebook 49 8

Repositories

Showing 10 of 24 repositories
  • param-decomp Public

    Parameter Decomposition

    goodfire-ai/param-decomp's past year of commit activity
    Python 142 MIT 54 12 (1 issue needs help) 6 Updated Sep 8, 2026
  • causalab Public
    goodfire-ai/causalab's past year of commit activity
    Python 114 39 16 0 Updated Sep 1, 2026
  • goodfire-ai/block-sparse-featurizer's past year of commit activity
    Jupyter Notebook 37 MIT 9 1 0 Updated Aug 17, 2026
  • toolathlon-runtime Public

    Reusable runtime for sandboxed tool-use tasks

    goodfire-ai/toolathlon-runtime's past year of commit activity
    Dockerfile 0 Apache-2.0 0 0 0 Updated Aug 9, 2026
  • goodfire-ai/esm-c-structure-demo's past year of commit activity
    HTML 0 0 0 0 Updated Aug 2, 2026
  • evee-manuscript Public

    Manuscript figures and panel data for the EVEE (Evo Variant Effect Explorer) paper

    goodfire-ai/evee-manuscript's past year of commit activity
    Python 18 0 1 0 Updated Jul 6, 2026
  • mtbbench Public Forked from bunnelab/mtbbench

    MTBBench is a benchmark designed to evaluate the reasoning capabilities of multimodal large language models (LLMs) in complex clinical decision-making scenarios. It focuses on two core challenges in oncology: multimodal integration (e.g., pathology, genomics, radiology) and longitudinal reasoning across patient timelines.

    goodfire-ai/mtbbench's past year of commit activity
    Python 0 MIT 8 0 0 Updated Jun 24, 2026
  • LLM_RAG_Agent Public Forked from Dyke-F/LLM_RAG_Agent
    goodfire-ai/LLM_RAG_Agent's past year of commit activity
    Python 1 MIT 12 0 0 Updated Jun 24, 2026
  • pages-p13c22bca-labels Public

    GitHub Pages site: p13c22bca-labels (component labels viewer)

    goodfire-ai/pages-p13c22bca-labels's past year of commit activity
    HTML 0 0 0 0 Updated Jun 24, 2026
  • pages-labels-p13c22bca Public

    GitHub Pages site: autointerp labels for p-13c22bca

    goodfire-ai/pages-labels-p13c22bca's past year of commit activity
    HTML 0 0 0 0 Updated Jun 24, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…