© 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. 125956
    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
    854
    -0.07
    undler
    -0.07
     preschool
    -0.06
    otland
    -0.06
    aho
    -0.06
    okud
    -0.06
    624
    -0.06
    iddi
    -0.06
    ASHINGTON
    -0.06
    :UI
    -0.06
    POSITIVE LOGITS
    ýt
    0.07
    umlu
    0.07
    LLU
    0.07
     gan
    0.07
     Ortiz
    0.06
     Äiju
    0.06
    prog
    0.06
     GANG
    0.06
    beck
    0.06
     gren
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.