Researchers used sparse autoencoders (SAEs) to identify components of the Llama 70B model's internal processing associated with deceptive outputs to determine if the model's claims of consciousness were merely sophisticated role-play.

Authors

• Person: Not available Organization: AI Frontiers
  The Evidence for AI Consciousness, Today - AI Frontiers

Sources

• The Evidence for AI Consciousness, Today - AI Frontiers ai-frontiers.org AI Frontiers via serper

Referenced by nodes (1)

• consciousness concept