cd/entity/WildJailBreak Bench· home› entities› WildJailBreak Bench
grep -l @wildjailbreak bench /news/*.json | wc -l → 1

WildJailBreak Bench

mentions 1 type Person feed RSS

// recent coverage 1 mentions

20:28
2026-08-04
lesswrong.com
ai-safety

Does Your LLM Trust You?

A study by an anonymous researcher, conducted as part of Neel Nanda's MATS 10.0 stream, found that linear 'trust' vectors extracted from the residual streams of Llama-3.2-3B-Instruct and Llama-3.1-8B-…

// co-occurs with top 6 entities
Neel Nanda 1 MATS 10.0 1 Llama-3.2-3B-Instruct 1 Llama-3.1-8B-Instruct 1 Chen et al. 1 Arditi et al. 1
// topics top 3 topics
ai safety 1 ai research 1 large language models 1