© 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. 71414
    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
     âĸ³
    -0.07
    ayıp
    -0.07
    سط
    -0.07
    ÌĢ
    -0.07
    FT
    -0.07
    ccount
    -0.07
    vero
    -0.06
     Sü
    -0.06
    airro
    -0.06
     peÄį
    -0.06
    POSITIVE LOGITS
    hek
    0.06
    essel
    0.06
    ialis
    0.06
    iene
    0.06
     Interracial
    0.06
    ses
    0.06
    Å¡etÅĻ
    0.06
    kos
    0.06
    annon
    0.06
    alla
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.