© 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. 18052
    Prev
    Next
    INDEX
    Explanations

    expressions related to medical conditions and treatment

    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
     Trem
    -0.06
    umas
    -0.06
    oggle
    -0.06
     Swe
    -0.06
    EventArgs
    -0.06
    829
    -0.06
     Singleton
    -0.06
     gastrointestinal
    -0.06
    .management
    -0.06
    neck
    -0.06
    POSITIVE LOGITS
     healing
    0.09
     Healing
    0.08
    olik
    0.07
     heal
    0.07
     recovery
    0.07
    .infinity
    0.07
    uming
    0.07
    antom
    0.07
    ereum
    0.07
     Cart
    0.07
    Activations Density 0.002%

    No Known Activations