AI RESEARCH
Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
arXiv CS.LG
•
ArXi:2605.15436v1 Announce Type: cross This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their performance on twelve cognitive task categories. Through systematic measurement of final activation values, attention entropy, and sparsity patterns, we reveal fundamental differences in how encoder and decoder architectures process diverse cognitive tasks.