Alternatives and similar repositories for vivaria:

Users that are interested in vivaria are comparing it to the libraries listed below

• METR / task-standard
  METR Task Standard
  ☆147Updated 2 months ago
• poking-agents / modular-public
  ☆21Updated 2 weeks ago
• METR / public-tasks
  ☆87Updated last month
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆112Updated this week
• google-deepmind / dangerous-capability-evaluations
  ☆53Updated 6 months ago
• METR / RE-Bench
  ☆71Updated 2 months ago
• emergent-misalignment / emergent-misalignment
  ☆130Updated last month
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆172Updated 5 months ago
• google-deepmind / mishax
  ☆128Updated 2 weeks ago
• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆48Updated this week
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year
• Cadenza-Labs / sleeper-agents
  ☆10Updated 9 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆239Updated 3 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 …
  ☆166Updated this week
• METR / task-template
  ☆9Updated 8 months ago
• haizelabs / verdict
  Verdict is a library for scaling judge-time compute.
  ☆195Updated 3 weeks ago
• OpenPipe / ART
  OpenPipe ART (Agent Reinforcement Trainer): train LLM agents
  ☆77Updated this week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆100Updated last year
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆53Updated 2 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆194Updated 4 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆118Updated 2 years ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆94Updated last month
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 2 years ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆26Updated last year
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆82Updated this week
• leap-laboratories / PIZZA
  An attribution library for LLMs
  ☆38Updated 6 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆198Updated last week
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆167Updated last month
• amack315 / unsupervised-steering-vectors
  ☆30Updated 11 months ago