© 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. 54619
    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
    .scalablytyped
    -0.09
    auer
    -0.07
     Religious
    -0.07
    endon
    -0.07
    reet
    -0.07
     Canter
    -0.07
    wat
    -0.07
    íĥĿ
    -0.07
    shaw
    -0.06
    unsch
    -0.06
    POSITIVE LOGITS
    nul
    0.06
    asl
    0.06
    .DataType
    0.06
    ENDOR
    0.06
     بÙĪابة
    0.06
    resentation
    0.06
     Outer
    0.06
    LIK
    0.06
    ewis
    0.06
    TERS
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.