# AVSS: Layer Importance Evaluation in Large Language Models via Activation Variance-Sparsity Analysis

arXiv: https://arxiv.org/abs/2411.02117 · HTML: https://mlsanity.com/paper/2411.02117/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 12 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 4 of 4)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)

## Built on by (most cited first, 1 of 1)

- [EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling](https://mlsanity.com/paper/2412.17249/) (2024)

## Abstract (arXiv)

The evaluation of layer importance in deep learning has been an active area of research, with significant implications for model optimization and interpretability. Recently, large language models (LLMs) have gained prominence across various domains, yet limited studies have explored the functional importance and performance contributions of individual layers within LLMs, especially from the perspective of activation distribution. In this work, we propose the Activation Variance-Sparsity Score (AVSS), a novel metric combining normalized activation variance and sparsity to assess each layer's contribution to model performance. By identifying and removing approximately the lowest 25% of layers based on AVSS, we achieve over 90% of original model performance across tasks such as question answering, language modeling, and sentiment classification, indicating that these layers may be non-essential. Our approach provides a systematic method for identifying less critical layers, contributing to efficient large language model architectures.