© 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. 118496
    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
    ï¼ı
    -0.08
     folks
    -0.07
    renom
    -0.06
    .sourceforge
    -0.06
    erton
    -0.06
    ocio
    -0.06
     عص
    -0.06
    ãĥ¬ãĥ³
    -0.06
    à¸į
    -0.06
    leta
    -0.06
    POSITIVE LOGITS
     Cly
    0.07
     Contrib
    0.07
    _pending
    0.07
     Pending
    0.06
     pending
    0.06
    ocaly
    0.06
    .scenes
    0.06
    (undefined
    0.06
     Crown
    0.06
    wise
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.