2026
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Cristian Hinostroza, Rodrigo Toro Icarte, Christ Devia, Andres Carvallo De Ferari, Eugenio Herrera-Berg, Denis Parra +1
ICLR 2026poster
Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized architectures. Mechanistic interpretability has led to the development of various methods for assessing layer relevance, wi…