© 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. 38931
    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
    icker
    -0.06
    .metamodel
    -0.06
    lü
    -0.06
     kork
    -0.06
    urst
    -0.06
    /spec
    -0.06
    .setter
    -0.06
    ¢åįķ
    -0.06
    svp
    -0.06
    ein
    -0.06
    POSITIVE LOGITS
    rai
    0.06
     Fulton
    0.06
    çİ
    0.06
     Bilim
    0.06
    æĿī
    0.05
     fir
    0.05
    (*(
    0.05
     Cold
    0.05
    .Multiline
    0.05
    ĩĮ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.