© 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. 93037
    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
    ycz
    -0.09
    otti
    -0.06
    uby
    -0.06
    IGH
    -0.06
     Knot
    -0.06
    loven
    -0.06
     defer
    -0.06
    OTH
    -0.06
    urn
    -0.06
     iVar
    -0.06
    POSITIVE LOGITS
     yourselves
    0.07
    loadModel
    0.06
    .spatial
    0.06
    æĽ¸é¤¨
    0.06
     Cuisine
    0.06
    bos
    0.06
     Mandela
    0.06
    аÑĤе
    0.06
    à¸Ļาà¸Ķ
    0.06
    .paths
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.