Alternatives and similar repositories for sleeper-agents:

Users that are interested in sleeper-agents are comparing it to the libraries listed below

• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆16Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆233Updated 3 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆90Updated last month
• ArthurConmy / Automatic-Circuit-Discovery
  ☆211Updated 5 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆45Updated 4 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆86Updated last month
• METR / task-standard
  METR Task Standard
  ☆144Updated last month
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• amack315 / unsupervised-steering-vectors
  ☆29Updated 10 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆83Updated this week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆161Updated this week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 3 months ago
• redwoodresearch / alignment_faking_public
  ☆41Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆59Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆129Updated 9 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆206Updated last year
• neelnanda-io / Crosscoders
  ☆32Updated 4 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆189Updated 3 months ago
• poking-agents / modular-public
  ☆15Updated 3 weeks ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• METR / public-tasks
  ☆85Updated this week
• METR / RE-Bench
  ☆65Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆224Updated last year
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆72Updated 2 years ago
• jacobdunefsky / transcoder_circuits
  ☆61Updated 4 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆30Updated 9 months ago