Alternatives and similar repositories for BELLS

Users that are interested in BELLS are comparing it to the libraries listed below

• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆129Updated this week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆290Updated this week
• UKGovernmentBEIS / hibayes
  ☆36Updated last month
• METR / task-standard
  METR Task Standard
  ☆168Updated 9 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆116Updated 5 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆302Updated 11 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆384Updated last year
• goodfire-ai / scribe
  ☆54Updated 2 months ago
• UKGovernmentBEIS / inspect_ai
  Inspect: A framework for large language model evaluations
  ☆1,506Updated last week
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆17Updated last week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆707Updated this week
• Giskard-AI / awesome-ai-safety
  📚 A curated list of papers & technical articles on AI Quality & Safety
  ☆193Updated 7 months ago
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆834Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• compl-ai / compl-ai
  An open-source compliance-centered evaluation framework for Generative AI models
  ☆172Updated 2 weeks ago
• TransluceAI / docent
  ☆63Updated 2 months ago
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆509Updated this week
• aiverify-foundation / moonshot
  Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
  ☆285Updated 2 months ago
• centerforaisafety / Intro_to_ML_Safety
  ☆75Updated 2 years ago
• rgreenblatt / control-evaluations
  ☆20Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆302Updated 5 months ago
• aiverify-foundation / aiverify
  AI Verify
  ☆37Updated 3 weeks ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆214Updated last year
• Data-Provenance-Initiative / Data-Provenance-Collection
  ☆257Updated 8 months ago
• decoderesearch / SAELens
  Training Sparse Autoencoders on Language Models
  ☆1,075Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆75Updated 2 years ago
• saprmarks / dictionary_learning
  ☆367Updated 3 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆244Updated last year