Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Layers at Similar Depths Generate Similar Activations Across LLM Architectures
Christopher Wolfram, Aaron Schein
How do the latent spaces used by independently-trained LLMs relate to one another? We study the nearest neighbor relationships induced by activations at different layers of 24 open…
cs.CL2025
Linear Representations of Political Perspective Emerge in Large Language Models
Junsol Kim, James Evans, Aaron Schein
Large language models (LLMs) have demonstrated the ability to generate text that realistically reflects a range of different subjective human perspectives. This paper studies how L…