Alternatives and similar repositories for sonar

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

• JasonGross / guarantees-based-mechanistic-interpretability
  ☆14Updated last week
• google-deepmind / mishax
  ☆129Updated last month
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆131Updated 3 weeks ago
• pyember / ember
  ☆172Updated last month
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆92Updated this week
• apple / pfl-research
  Simulation framework for accelerating research in Private Federated Learning
  ☆327Updated this week
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆70Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆102Updated last year
• haizelabs / verdict
  Verdict is a library for scaling judge-time compute.
  ☆211Updated 2 weeks ago
• ulab-uiuc / tiny-scientist
  A lightweight framework for building research agents designed for developers
  ☆84Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…
  ☆57Updated this week
• aidecentralized / nanda-servers
  A catalogue of existing Nanda servers
  ☆119Updated 3 weeks ago
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 7 months ago
• METR / RE-Bench
  ☆74Updated 3 weeks ago
• poking-agents / modular-public
  ☆22Updated last week
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆173Updated 2 months ago
• morph-labs / morphcloud-examples-public
  anything you want can be built with morph cloud
  ☆12Updated 2 weeks ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆122Updated 2 years ago
• centerforaisafety / Intro_to_ML_Safety
  ☆68Updated last year
• METR / task-standard
  METR Task Standard
  ☆146Updated 3 months ago
• neelnanda-io / Grokking
  A Mechanistic Interpretability Analysis of Grokking
  ☆21Updated 2 years ago
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆118Updated this week
• princeton-pli / hal-harness
  ☆78Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆245Updated 5 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆203Updated 7 months ago
• emergent-misalignment / emergent-misalignment
  ☆148Updated 2 months ago
• epfml / disco
  DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning …
  ☆166Updated this week
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆54Updated 3 months ago
• ApolloResearch / sample
  Repository with sample code using Apollo's suggested engineering practices
  ☆9Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆182Updated 6 months ago