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.
  ☆153Updated last week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆357Updated last week
• METR / task-standard
  METR Task Standard
  ☆173Updated last year
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆391Updated last year
• UKGovernmentBEIS / inspect_ai
  Inspect: A framework for large language model evaluations
  ☆1,727Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆320Updated last year
• aiverify-foundation / moonshot
  Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
  ☆310Updated last week
• UKGovernmentBEIS / hibayes
  ☆40Updated 3 weeks ago
• centerforaisafety / Intro_to_ML_Safety
  ☆77Updated 2 years ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆76Updated 2 years ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆291Updated last year
• haizelabs / redteaming-resistance-benchmark
  ☆50Updated last year
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆800Updated last week
• ajobi-uhc / seer
  This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …
  ☆121Updated 3 weeks ago
• compl-ai / compl-ai
  An open-source compliance-centered evaluation framework for Generative AI models
  ☆179Updated this week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆567Updated 6 months ago
• decoderesearch / SAELens
  Training Sparse Autoencoders on Language Models
  ☆1,201Updated this week
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆17Updated last week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆127Updated last year
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆857Updated 2 weeks ago
• Giskard-AI / awesome-ai-safety
  📚 A curated list of papers & technical articles on AI Quality & Safety
  ☆201Updated 9 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆258Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆126Updated last month
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆240Updated last year
• aiverify-foundation / aiverify
  AI Verify
  ☆47Updated 3 weeks ago
• goodfire-ai / scribe
  ☆70Updated last month
• mlcommons / modelbench
  Run safety benchmarks against AI models and view detailed reports showing how well they performed.
  ☆117Updated last week
• centerforaisafety / HarmBench
  HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
  ☆847Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆340Updated 7 months ago
• saprmarks / dictionary_learning
  ☆389Updated 5 months ago