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
  ☆20Updated 7 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆55Updated 7 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆108Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆25Updated 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…
  ☆69Updated this week
• neelnanda-io / Crosscoders
  ☆44Updated 7 months ago
• redwoodresearch / alignment_faking_public
  ☆65Updated last month
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆158Updated last year
• adamkarvonen / SAEBench
  ☆101Updated 3 weeks ago
• METR / RE-Bench
  ☆84Updated 2 months ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆35Updated last year
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• ApolloResearch / sample
  Repository with sample code using Apollo's suggested engineering practices
  ☆9Updated 6 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆226Updated 8 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…
  ☆27Updated last year
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 6 months ago
• saprmarks / feature-circuits
  ☆173Updated 2 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆35Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆94Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• METR / task-standard
  METR Task Standard
  ☆151Updated 4 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆257Updated 6 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆18Updated 8 months ago