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.
  ☆150Updated this week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆349Updated this week
• haizelabs / redteaming-resistance-benchmark
  ☆50Updated last year
• METR / task-standard
  METR Task Standard
  ☆172Updated 11 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆390Updated last year
• Giskard-AI / awesome-ai-safety
  📚 A curated list of papers & technical articles on AI Quality & Safety
  ☆199Updated 9 months ago
• UKGovernmentBEIS / inspect_ai
  Inspect: A framework for large language model evaluations
  ☆1,712Updated this week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆124Updated last year
• UKGovernmentBEIS / hibayes
  ☆39Updated 2 weeks ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆289Updated last year
• compl-ai / compl-ai
  An open-source compliance-centered evaluation framework for Generative AI models
  ☆178Updated last month
• centerforaisafety / HarmBench
  HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
  ☆841Updated last year
• aiverify-foundation / moonshot
  Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
  ☆306Updated last week
• emergent-misalignment / emergent-misalignment
  ☆257Updated 3 weeks ago
• centerforaisafety / Intro_to_ML_Safety
  ☆77Updated 2 years ago
• mlcommons / modelbench
  Run safety benchmarks against AI models and view detailed reports showing how well they performed.
  ☆117Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆318Updated last year
• AI-secure / DecodingTrust
  A Comprehensive Assessment of Trustworthiness in GPT Models
  ☆310Updated last year
• aiverify-foundation / aiverify
  AI Verify
  ☆46Updated 2 weeks ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆124Updated last month
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆255Updated last year
• GraySwanAI / nanoGCG
  A fast + lightweight implementation of the GCG algorithm in PyTorch
  ☆313Updated 8 months ago
• JasonGross / guarantees-based-mechanistic-interpretability
  ☆17Updated this week
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆675Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆76Updated 2 years ago
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆159Updated 8 months ago
• agencyenterprise / PromptInject
  PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…
  ☆451Updated last year
• goodfire-ai / scribe
  ☆66Updated 3 weeks ago
• ServiceNow / DoomArena
  DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats
  ☆51Updated 4 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆565Updated 5 months ago