Alternatives and similar repositories for BELLS

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

• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆272Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆115Updated this week
• METR / task-standard
  METR Task Standard
  ☆163Updated 8 months ago
• compl-ai / compl-ai
  An open-source compliance-centered evaluation framework for Generative AI models
  ☆169Updated this week
• UKGovernmentBEIS / hibayes
  ☆35Updated last week
• UKGovernmentBEIS / inspect_ai
  Inspect: A framework for large language model evaluations
  ☆1,431Updated last week
• Giskard-AI / awesome-ai-safety
  📚 A curated list of papers & technical articles on AI Quality & Safety
  ☆192Updated 6 months ago
• haizelabs / redteaming-resistance-benchmark
  ☆49Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆120Updated last year
• aiverify-foundation / aiverify
  AI Verify
  ☆36Updated 3 weeks ago
• emergent-misalignment / emergent-misalignment
  ☆222Updated 7 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆238Updated last year
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆375Updated last year
• aiverify-foundation / moonshot
  Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
  ☆278Updated last month
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆292Updated 4 months ago
• centerforaisafety / Intro_to_ML_Safety
  ☆75Updated 2 years ago
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆16Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆296Updated 10 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆278Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆209Updated 11 months ago
• AI-secure / DecodingTrust
  A Comprehensive Assessment of Trustworthiness in GPT Models
  ☆306Updated last year
• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆235Updated 8 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆118Updated last week
• GraySwanAI / nanoGCG
  A fast + lightweight implementation of the GCG algorithm in PyTorch
  ☆295Updated 5 months ago
• centerforaisafety / HarmBench
  HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
  ☆760Updated last year
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
  ☆357Updated 9 months ago
• saprmarks / dictionary_learning
  ☆355Updated 2 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆112Updated 4 months ago
• goodfire-ai / scribe
  ☆47Updated last month