© 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. 89387
    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
     Hav
    -0.07
     Federation
    -0.07
    uard
    -0.07
    annel
    -0.07
    Ñīин
    -0.07
    iego
    -0.06
    urai
    -0.06
    ochen
    -0.06
    ĶåĽŀ
    -0.06
    ä¸īå¹´
    -0.06
    POSITIVE LOGITS
    -collection
    0.06
     ThemeData
    0.06
    aras
    0.06
    rig
    0.05
    inx
    0.05
    TOTYPE
    0.05
    otel
    0.05
     маÑģÑĤ
    0.05
    BJ
    0.05
    YLE
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.