© 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. 2313
    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
    zh
    -0.06
     Clip
    -0.06
    sv
    -0.06
    .pixel
    -0.06
    Canceled
    -0.06
     Ryder
    -0.06
     Harbor
    -0.06
     OK
    -0.06
     peoples
    -0.06
     جÙĨ
    -0.06
    POSITIVE LOGITS
    utzer
    0.07
    odia
    0.07
    ̧
    0.07
    ализи
    0.07
    undler
    0.07
    Çİ
    0.07
    ieber
    0.07
    ylko
    0.06
    inson
    0.06
    ftar
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.