© 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. 27707
    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
    able
    -0.07
     Sez
    -0.06
    ates
    -0.06
    rava
    -0.06
     Chow
    -0.06
     Vig
    -0.06
    ÑĮÑİ
    -0.06
    ArrayOf
    -0.06
    filer
    -0.06
    oder
    -0.05
    POSITIVE LOGITS
    ÎĮ
    0.07
    ãĤ«ãĥĨ
    0.07
     migrationBuilder
    0.07
    алог
    0.07
    usra
    0.07
    ::__
    0.06
    %%↵
    0.06
    teil
    0.06
    ÎĪ
    0.06
    ProgressHUD
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.