© 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. 72101
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    elight
    -0.07
    strcasecmp
    -0.07
    idor
    -0.06
    ůvod
    -0.06
    DP
    -0.06
    аÑĢÑĩ
    -0.06
    vant
    -0.06
     réfé
    -0.06
    entes
    -0.06
     guit
    -0.06
    POSITIVE LOGITS
    ix
    0.07
    akin
    0.07
    chn
    0.07
    anner
    0.07
    ortal
    0.06
     Barton
    0.06
    ixon
    0.06
    /uploads
    0.06
    atoria
    0.06
    ces
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.