© 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. 15-LLAMASCOPE-RES-131K
    11. 717
    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
     Dos
    -0.07
    oba
    -0.07
    czy
    -0.06
    /assert
    -0.06
    ãĥ¡ãĥ©
    -0.06
     Ski
    -0.06
     zip
    -0.06
    cade
    -0.06
     ostr
    -0.06
     wal
    -0.05
    POSITIVE LOGITS
    regor
    0.08
    é£
    0.07
    ENDING
    0.07
    yling
    0.07
    uppe
    0.06
    .onPause
    0.06
     é£
    0.06
    aminer
    0.06
    oeff
    0.06
    -ending
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.