SAE features reveal an "Immersive Simulation Mode" inside LLMs during roleplay

sebkrier · x · 2026-09-13

A new study uses Sparse Autoencoder (SAE) features as components in Gemma and Llama to examine what happens internally when an LLM switches from the default Assistant to a roleplay persona or a story character. Two findings:

Original post →

More from Research

Research channel →