cd/entity/Llama-3.2-3B-Instruct· home› entities› Llama-3.2-3B-Instruct
grep -l @llama-3.2-3b-instruct /news/*.json | wc -l → 2

Llama-3.2-3B-Instruct

mentions 2 type Organization feed RSS

// recent coverage 2 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 8 entities
SMDA 1 Meta 1 Neel Nanda 1 MATS 10.0 1 Llama-3.1-8B-Instruct 1 Chen et al. 1 Arditi et al. 1 WildJailBreak Bench 1
// topics top 5 topics
ai safety 2 large language models 2 ai research 2 ai ethics 1 machine learning 1