Alternatives and similar repositories for dangerous-capability-evaluations

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

• METR / RE-Bench
  ☆113Updated last week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆119Updated last year
• google-deepmind / mishax
  ☆142Updated last month
• METR / task-standard
  METR Task Standard
  ☆163Updated 8 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆116Updated this week
• 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
• aypan17 / machiavelli
  ☆138Updated 3 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• 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"
  ☆71Updated last year
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆38Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆264Updated this week
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆94Updated 2 years ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆163Updated 6 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆110Updated 8 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆209Updated 2 weeks ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆104Updated last week
• METR / public-tasks
  ☆104Updated last week
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆89Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 5 months ago
• MinhxLe / subliminal-learning
  ☆98Updated 2 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆82Updated 11 months ago
• cohere-ai / magikarp
  Code for the paper "Fishing for Magikarp"
  ☆171Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆126Updated 8 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• Aleph-Alpha-Research / scaling
  Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…
  ☆64Updated 3 weeks ago
• thestephencasper / everything-you-need
  we got you bro
  ☆36Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆209Updated 11 months ago
• emergent-misalignment / emergent-misalignment
  ☆220Updated 7 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆219Updated last week