Meg Tong

Meg Tong on Hugging Face Daily Papers: 4 papers, 0 in the top 3 of their day, 59 upvotes.

1. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming 8 upvotes, #8 of 2025-02-03
2. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training 30 upvotes, #5 of 2024-01-12
3. Steering Llama 2 via Contrastive Activation Addition 12 upvotes, #7 of 2023-12-13
4. Towards Understanding Sycophancy in Language Models 7 upvotes, #14 of 2023-10-23

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.