Alternatives and similar repositories for dangerous-capability-evaluations

Users that are interested in dangerous-capability-evaluations are comparing it to the libraries listed below

• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆118Updated last year
• METR / RE-Bench
  ☆102Updated 5 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
• google-deepmind / mishax
  ☆142Updated 3 weeks ago
• METR / task-standard
  METR Task Standard
  ☆162Updated 8 months ago
• aypan17 / machiavelli
  ☆138Updated 2 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆93Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆241Updated this week
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆72Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆111Updated this week
• METR / public-tasks
  ☆104Updated last week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆208Updated this week
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆160Updated 5 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆74Updated last week
• ApolloResearch / insider-trading
  ☆53Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆99Updated this week
• MinhxLe / subliminal-learning
  ☆97Updated 2 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆36Updated last year
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆109Updated 7 months ago
• safety-research / open-source-alignment-faking
  Open Source Replication of Anthropic's Alignment Faking Paper
  ☆51Updated 6 months ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• haizelabs / bijection-learning
  ☆26Updated 11 months ago
• emergent-misalignment / emergent-misalignment
  ☆216Updated 7 months ago
• anthropics / evals
  ☆301Updated last year
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆89Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆215Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• princeton-pli / hal-harness
  ☆136Updated this week