Alternatives and similar repositories for control-evaluations

Users that are interested in control-evaluations 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.
  ☆76Updated this week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆109Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆186Updated this week
• centerforaisafety / Intro_to_ML_Safety
  ☆72Updated 2 years ago
• METR / task-standard
  METR Task Standard
  ☆154Updated 5 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 8 months ago
• redwoodresearch / alignment_faking_public
  ☆69Updated last month
• emergent-misalignment / emergent-misalignment
  ☆171Updated 4 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆59Updated last month
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆117Updated 5 months ago
• METR / RE-Bench
  ☆92Updated 2 months ago
• Cadenza-Labs / sleeper-agents
  ☆11Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆112Updated last year
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆113Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆217Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆52Updated last week
• aypan17 / machiavelli
  ☆137Updated 8 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆365Updated 8 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• saprmarks / feature-circuits
  ☆181Updated last week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆265Updated 7 months ago
• haizelabs / redteaming-resistance-benchmark
  ☆45Updated 11 months ago
• METR / public-tasks
  ☆99Updated 4 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• safety-research / safety-examples
  ☆16Updated 3 weeks ago
• Algorithmic-Alignment-Lab / contracts
  Formal Contracts for Multi-Agent Reinforcement Learning
  ☆19Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆243Updated last month
• maxdreyer / PURE
  Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…
  ☆16Updated last year
• jacobdunefsky / transcoder_circuits
  ☆148Updated 8 months ago