© 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. 116839
    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
    achat
    -0.07
     Universe
    -0.07
    usher
    -0.06
    .SplitContainer
    -0.06
    UserCode
    -0.06
    à¥įयम
    -0.06
    :message
    -0.06
    eniz
    -0.06
    ItemAt
    -0.06
    алÑĮне
    -0.06
    POSITIVE LOGITS
    semb
    0.06
     Kür
    0.06
    piel
    0.06
    Ķ
    0.06
    etz
    0.06
    (
    0.06
    zig
    0.06
     Suppress
    0.06
    iesta
    0.06
     Naw
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.