© 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. 73751
    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
    uchar
    -0.08
    (æ°´
    -0.08
    ãİ
    -0.08
    ë¨
    -0.08
    upplier
    -0.08
    _via
    -0.07
    ỳ
    -0.07
    ÏĦαι
    -0.07
    OUCH
    -0.07
    (æľ¨
    -0.07
    POSITIVE LOGITS
     people
    0.07
    oris
    0.06
    \-
    0.06
    omas
    0.06
     zwar
    0.06
    éĩĮéĿ¢
    0.06
     when
    0.06
    rible
    0.06
    bert
    0.06
     lots
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.