© 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. 120489
    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
    odie
    -0.06
     PRI
    -0.06
    757
    -0.06
     complete
    -0.06
    hangi
    -0.06
    TOT
    -0.06
    ovsky
    -0.06
     Noon
    -0.06
     artificial
    -0.06
    kish
    -0.06
    POSITIVE LOGITS
     fucked
    0.07
    .Void
    0.07
     âĸĪ
    0.06
    <decltype
    0.06
    ừ
    0.06
    εÏĩ
    0.06
    -ÑĤо
    0.06
    anton
    0.06
    laz
    0.06
     Celt
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.