© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56373
    Prev
    Next
    INDEX
    Explanations

    references to hospitals and medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åį«çĶŁ
    -0.07
     sickness
    -0.07
    utra
    -0.07
    éijij
    -0.07
    Raises
    -0.07
    ycastle
    -0.07
    .Utility
    -0.07
    apikey
    -0.07
    ãģĵãģĿ
    -0.06
    norm
    -0.06
    POSITIVE LOGITS
     expertise
    0.08
     team
    0.08
     expert
    0.07
     teams
    0.07
    team
    0.06
     inherited
    0.06
    expert
    0.06
     multid
    0.06
     experts
    0.06
     consulta
    0.06
    Activations Density 0.015%

    No Known Activations