Understanding the internal computations of large language models (LLMs) is crucial for aligning them with human values and preventing undesirable behaviors like toxic content generation. However, mechanistic interpretability is hindered by polysemanticity -- where individual neurons respond to multiple, unrelated concepts. While Sparse Autoencoders (SAEs) have attempted to disentangle these features through sparse dictionary learning, they have compromised LLM performance due to reliance on post-hoc reconstruction loss. To address this issue, we introduce Mixture of Monosemantic Experts for Transformers (Monet) architecture, which incorporates sparse dictionary learning directly into end-to-end Mixture-of-Experts pretraining. Our novel expert decomposition method enables scaling the expert count to 262,144 per layer while total parameters scale proportionally to the square root of the number of experts. Our analyses demonstrate mutual exclusivity of knowledge across experts and showcase the parametric knowledge encapsulated within individual experts. Moreover, Monet allows knowledge manipulation over domains, languages, and toxicity mitigation without degrading general performance. Our pursuit of transparent LLMs highlights the potential of scaling expert counts to enhance} mechanistic interpretability and directly resect the internal knowledge to fundamentally adjust} model behavior. The source code and pretrained checkpoints are available at https://github.com/dmis-lab/Monet.

翻译：理解大型语言模型（LLM）的内部计算机制对于使其与人类价值观对齐、防止生成有害内容等不良行为至关重要。然而，机制可解释性受到多义性（即单个神经元对多个不相关概念产生响应）的阻碍。尽管稀疏自编码器（SAE）尝试通过稀疏字典学习来解耦这些特征，但由于依赖事后重建损失，它们往往以牺牲LLM性能为代价。为解决这一问题，我们提出了面向Transformer的单语义专家混合架构（Monet），该架构将稀疏字典学习直接集成到端到端的专家混合预训练中。我们新颖的专家分解方法使得每层专家数量可扩展至262,144个，而总参数数量仅与专家数量的平方根成比例增长。分析表明专家间知识具有互斥性，并展示了封装在单个专家内的参数化知识。此外，Monet支持在不降低通用性能的前提下，对领域知识、语言特性及毒性缓解进行知识操控。我们对透明化LLM的探索表明，通过扩展专家数量可增强机制可解释性，并能直接切除内部知识以根本性调整模型行为。源代码与预训练检查点已发布于https://github.com/dmis-lab/Monet。