cd/entity/Natural Language Autoencoder· home› entities› Natural Language Autoencoder

grep -l @natural language autoencoder /news/*.json | wc -l → 2

Natural Language Autoencoder

mentions 2 type Person feed RSS

// recent coverage 2 mentions

23:57

2026-07-29

lesswrong.com

artificial-intelligence

Intentional Control of Internal States in Gemma 3 27B

A replication of Anthropic's intentional control experiment on Gemma 3 27B Instruct found that the model has a stronger internal representation of a concept when told to think about it while writing a…

00:57

2026-07-24

lesswrong.com

ai-research

Fixing rewards for NLA to reduce confabulation

A researcher testing Anthropic's Natural Language Autoencoder (NLA) found that improving reconstruction fidelity does not guarantee faithful interpretation of a language model's internal activations. …

// co-occurs with top 8 entities

Anthropic 2 Gemma 3 27B Instruct 1 Claude 1 Gemma Scope 2 1 ARBOx4 1 Qwen 3.6-27B 1 ICLR 2027 1 Lesswrong 1

// topics top 4 topics

ai research 2 ai safety 2 artificial intelligence 1 large language models 1