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 suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆61Updated this week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆144Updated this week
• haizelabs / redteaming-resistance-benchmark
  ☆44Updated 10 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆106Updated last year
• Giskard-AI / awesome-ai-safety
  📚 A curated list of papers & technical articles on AI Quality & Safety
  ☆182Updated last month
• METR / task-standard
  METR Task Standard
  ☆148Updated 4 months ago
• centerforaisafety / Intro_to_ML_Safety
  ☆70Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆253Updated 5 months ago
• ARBORproject / arborproject.github.io
  ☆75Updated 3 months ago
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆14Updated this week
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆353Updated 7 months ago
• compl-ai / compl-ai
  An open-source compliance-centered evaluation framework for Generative AI models
  ☆152Updated last month
• google-deepmind / mishax
  ☆131Updated 2 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆214Updated last year
• JailbreakBench / jailbreakbench
  JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
  ☆347Updated 2 months ago
• METR / public-tasks
  ☆96Updated 2 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆69Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆248Updated 10 months ago
• EffiSciencesResearch / ML4G
  Machine Learning for Alignment Bootcamp
  ☆25Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆48Updated last week
• iamgroot42 / mimir
  Python package for measuring memorization in LLMs.
  ☆156Updated 6 months ago
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆175Updated this week
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆209Updated 8 months ago
• AI-secure / DecodingTrust
  A Comprehensive Assessment of Trustworthiness in GPT Models
  ☆294Updated 8 months ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 10 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆223Updated 8 months ago
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
  ☆313Updated 4 months ago
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆110Updated last year
• holistic-ai / holisticai
  This is an open-source tool to assess and improve the trustworthiness of AI systems.
  ☆92Updated 3 weeks ago
• oxfordinternetinstitute / oxonfair
  Fairness toolkit for pytorch, scikit learn and autogluon
  ☆32Updated 5 months ago