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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54173
    Prev
    Next
    INDEX
    Explanations

    references to medical specialists and their roles

    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
    ponder
    -0.07
     addCriterion
    -0.07
    æŃ
    -0.07
    ãĢĤãĢĤ↵↵
    -0.07
    sz
    -0.07
    _IMPLEMENT
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
    Ñĩна
    -0.07
    .Manager
    -0.07
    gran
    -0.07
    POSITIVE LOGITS
     experts
    0.15
     expert
    0.14
     expertise
    0.13
     specialists
    0.13
     specialist
    0.12
     Experts
    0.11
     Expert
    0.11
    expert
    0.10
    Experts
    0.09
     Specialist
    0.09
    Activations Density 0.159%

    No Known Activations