EUNO.NEWS EUNO.NEWS
  • All (2379) +221
  • AI (548) +19
  • DevOps (142) +2
  • Software (998) +131
  • IT (686) +68
  • Education (5) +1
  • Notice
  • All (2379) +221
    • AI (548) +19
    • DevOps (142) +2
    • Software (998) +131
    • IT (686) +68
    • Education (5) +1
  • Notice
  • All (2379) +221
  • AI (548) +19
  • DevOps (142) +2
  • Software (998) +131
  • IT (686) +68
  • Education (5) +1
  • Notice
Sources Tags Search
한국어 English 中文
  • 1周前 · ai

    [Paper] 辅助度量帮助解码真实环境中的技能神经元

    大型语言模型(LLMs)在广泛任务中展现出卓越的能力,但其内部机制仍然大多不透明。在本文中,w...

    #LLM interpretability #skill neurons #auxiliary metrics #neuron probing #model debugging
EUNO.NEWS
RSS GitHub © 2025