© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119777
    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
    iiii
    -0.07
    impse
    -0.07
    ìĽĥ
    -0.07
    iland
    -0.07
    862
    -0.06
    icol
    -0.06
    chw
    -0.06
    ÑĢов
    -0.06
    :frame
    -0.06
    758
    -0.06
    POSITIVE LOGITS
    ¥IJ
    0.07
     ((_
    0.06
    omik
    0.06
    onomous
    0.06
    BoundingBox
    0.06
    ceae
    0.06
     AndAlso
    0.06
    iversite
    0.06
    ÑĩаÑĤ
    0.06
     elektronik
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.