rlundqvist/eval-awareness-experiment-data download history

rlundqvist/eval-awareness-experiment-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 53 times (5 in the last 7 days), and 1,463 times in total. It ranks #177,952 among datasets by monthly downloads.

Evaluation Awareness Experiment Investigating whether LLMs exhibit different safety behaviors when they detect evaluative contexts in prompts, using Latent Direction Amplification (LDA) to causally manipulate eval-awareness signals. Quick Start # 1. Copy project to clus

Open rlundqvist/eval-awareness-experiment-data on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.