anthropics / sycophancy-to-subterfuge-paperLinks
☆23Updated 11 months ago
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".☆112Updated last year
- ☆98Updated 4 months ago
- ☆101Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 9 months ago
- Functional Benchmarks and the Reasoning Gap☆88Updated 11 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆110Updated last week
- ☆29Updated last year
- ☆141Updated 2 weeks ago
- 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
- An attribution library for LLMs☆42Updated 11 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- ☆25Updated 10 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- 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
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- ☆57Updated last month
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆89Updated last year
- Open source interpretability artefacts for R1.☆157Updated 4 months ago
- Measuring the situational awareness of language models☆38Updated last year
- Open Source Replication of Anthropic's Alignment Faking Paper☆50Updated 4 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆121Updated 6 months ago
- ☆72Updated last year
- METR Task Standard☆159Updated 7 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- ☆198Updated 5 months ago
- ☆293Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- Repository for the paper Stream of Search: Learning to Search in Language☆150Updated 7 months ago
- ☆33Updated last year
- Public Inflection Benchmarks☆68Updated last year