Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
Authors: Mahdi Naser-Moghadasi, Faezeh Ghaderi
Summary
arXiv:2605. 15436v1 Announce Type: new Abstract: 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.
Relevance
Read next because Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, rate, compare, language, model. Source: arxiv cs.CL (NLP).
Abstract
arXiv:2605.15436v1 Announce Type: new Abstract: 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. Our analysis of 144 task-model combinations demonstrates that mathematical reasoning consistently produces the highest attention entropy across all architectures, while decoder models exhibit significantly higher sparsity patterns compared to encoder models. The findings provide critical insights into the computational characteristics of modern language models and their task-specific neural behaviors, with implications for model selection and optimization in big data applications.