每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Jellyfish Family is an AI safety interpretability and purification module. It detects risky concept neurons within models and gently, yet effectively, removes harmful ones, preserving creativity an…