anthropics / sycophancy-to-subterfuge-paperLinks
☆24Updated last year
Alternatives and similar repositories for sycophancy-to-subterfuge-paper
Users that are interested in sycophancy-to-subterfuge-paper are comparing it to the libraries listed below
Sorting:
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆116Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- ☆103Updated this week
- ☆101Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆202Updated 10 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆111Updated this week
- Measuring the situational awareness of language models☆38Updated last year
- ☆142Updated 2 weeks ago
- ☆57Updated this week
- ☆300Updated last year
- Functional Benchmarks and the Reasoning Gap☆89Updated 11 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆183Updated 6 months ago
- Open Source Replication of Anthropic's Alignment Faking Paper☆50Updated 5 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Open source interpretability artefacts for R1.☆159Updated 5 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- An attribution library for LLMs☆42Updated last year
- Public Inflection Benchmarks☆68Updated last year
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- ☆206Updated 6 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 6 months ago
- ☆34Updated last year
- ☆81Updated this week
- ☆72Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 11 months ago
- METR Task Standard☆160Updated 7 months ago