© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75453
    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
    atten
    -0.08
    ÑĤоÑĦ
    -0.08
     darm
    -0.07
    ritz
    -0.07
    à¸ĵà¸ij
    -0.07
    анка
    -0.07
    ãĢĢãĥİ
    -0.07
    emmel
    -0.07
    è²´
    -0.07
     Kosten
    -0.07
    POSITIVE LOGITS
     fame
    0.06
    -f
    0.05
     famously
    0.05
     Zip
    0.05
    verage
    0.05
    adium
    0.05
     Marathon
    0.05
     pl
    0.05
     fl
    0.05
     bro
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.