© 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. 69489
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to diseases and conditions

    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
    apesh
    -0.07
    aben
    -0.07
     Sed
    -0.06
    okud
    -0.06
    ieme
    -0.06
    azon
    -0.06
    ohn
    -0.06
    ickness
    -0.06
    markets
    -0.06
     sed
    -0.06
    POSITIVE LOGITS
     presenting
    0.07
     delayed
    0.07
    Case
    0.06
     case
    0.06
     Late
    0.06
    case
    0.06
     presented
    0.06
     Case
    0.06
     coined
    0.06
    -case
    0.06
    Activations Density 0.011%

    No Known Activations