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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106854
    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
    emp
    -0.07
    engkap
    -0.06
    ongan
    -0.06
     æĤ
    -0.06
    owi
    -0.06
    /uploads
    -0.06
    ameda
    -0.06
    azu
    -0.06
    ilig
    -0.06
    unch
    -0.06
    POSITIVE LOGITS
     dias
    0.07
     ziy
    0.06
    iterations
    0.06
    azı
    0.06
     diy
    0.06
     ï
    0.06
    ìĿį
    0.06
    portun
    0.06
    -caret
    0.06
     guests
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.