© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126941
    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
     Rubin
    -0.07
     Spurs
    -0.07
    infeld
    -0.07
    iez
    -0.07
    .sales
    -0.07
    aga
    -0.06
    大人
    -0.06
     godt
    -0.06
    uchos
    -0.06
     Kits
    -0.06
    POSITIVE LOGITS
    GP
    0.07
     Crew
    0.07
     telemetry
    0.07
     driver
    0.07
     pit
    0.06
    .hom
    0.06
     dest
    0.06
     crew
    0.06
     race
    0.06
    oen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.