© 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. 104613
    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
    hart
    -0.06
    *)_
    -0.06
     Banks
    -0.06
    wing
    -0.06
    úsqueda
    -0.05
     diss
    -0.05
     hazards
    -0.05
    ":""
    -0.05
    itto
    -0.05
     critically
    -0.05
    POSITIVE LOGITS
    retty
    0.07
    ValidationError
    0.07
    imonial
    0.07
    (lo
    0.07
     nues
    0.07
    ÐłÐĿ
    0.07
    .community
    0.06
     gbc
    0.06
    ResponseBody
    0.06
    ej
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.