© 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. 40089
    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
    ibur
    -0.09
    ernen
    -0.07
    ennen
    -0.07
    ÑĮ
    -0.07
    otland
    -0.07
    opolitan
    -0.07
    frau
    -0.06
    THR
    -0.06
     subscribing
    -0.06
    :animated
    -0.06
    POSITIVE LOGITS
     Roz
    0.07
     overs
    0.07
     offline
    0.06
    rias
    0.06
    Offline
    0.06
    offline
    0.06
     Sund
    0.06
     piles
    0.06
    .face
    0.06
     digital
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.