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.
  ☆129Updated this week
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• TeunvdWeij / sandbagging
  ☆17Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆122Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆244Updated last year
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆65Updated 5 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆155Updated 6 months ago
• thestephencasper / explore_establish_exploit_llms
  ☆31Updated 2 years ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆145Updated 5 months ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆15Updated 7 months ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• METR / task-standard
  METR Task Standard
  ☆168Updated 9 months ago
• centerforaisafety / Intro_to_ML_Safety
  ☆75Updated 2 years ago
• tml-epfl / os-harm
  OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]
  ☆39Updated 2 months ago
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆32Updated last year
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆62Updated last year
• redwoodresearch / alignment_faking_public
  ☆81Updated last month
• aypan17 / machiavelli
  ☆142Updated 4 months ago
• ejones313 / auditing-llms
  ☆59Updated 2 years ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆116Updated 9 months ago
• emergent-misalignment / emergent-misalignment
  ☆228Updated last month
• safety-research / bloom
  bloom - evaluate any behavior immediately  🌸🌱
  ☆27Updated last week
• clarifying-EM / model-organisms-for-EM
  Code repo for the model organisms and convergent directions of EM papers.
  ☆40Updated 2 months ago
• saprmarks / feature-circuits
  ☆196Updated last month
• interp-reasoning / thought-anchors
  ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
  ☆92Updated last month
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆290Updated this week
• XuchanBao / behavioral-self-awareness
  ☆32Updated 9 months ago
• safety-research / persona_vectors
  Persona Vectors: Monitoring and Controlling Character Traits in Language Models
  ☆287Updated 4 months ago