anthropics / sycophancy-to-subterfuge-paper

Related projects ⓘ

Alternatives and complementary repositories for sycophancy-to-subterfuge-paper

• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆33Updated 9 months ago
• amack315 / unsupervised-steering-vectors
  ☆24Updated 6 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆106Updated last week
• LRudL / sad
  Situational Awareness Dataset
  ☆19Updated 3 weeks ago
• jbloomAus / SAEDashboard
  ☆20Updated last week
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆61Updated last 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…
  ☆25Updated 5 months ago
• google-deepmind / mishax
  ☆101Updated 3 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆154Updated last month
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆78Updated last month
• shauli-ravfogel / adv-kernel-removal
  ☆11Updated 2 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"
  ☆62Updated 5 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆63Updated this week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• jacobdunefsky / transcoder_circuits
  ☆44Updated this week
• METR / public-tasks
  ☆67Updated 3 weeks ago
• Aider-AI / aider-swe-bench
  Harness used to benchmark aider against SWE Bench benchmarks
  ☆53Updated 4 months ago
• JacobPfau / fillerTokens
  ☆49Updated 6 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated last month
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆16Updated 3 weeks ago
• milesaturpin / cot-unfaithfulness
  ☆32Updated last year
• KaiNylund / lm-weights-encode-time
  ☆68Updated 3 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆123Updated last month
• InflectionAI / Inflection-Benchmarks
  Public Inflection Benchmarks
  ☆69Updated 8 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆84Updated 8 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆84Updated 8 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆31Updated last month
• nickkeesG / Pantheon
  Experimental LLM interface exploring new ways to use AI to improve human thinking
  ☆13Updated last week