Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56234
    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
    ий
    -0.07
    cea
    -0.07
    baugh
    -0.06
    SEQ
    -0.06
    ENS
    -0.06
    mp
    -0.06
     competitor
    -0.06
    imet
    -0.06
    kov
    -0.06
    fast
    -0.05
    POSITIVE LOGITS
    orners
    0.07
    .opend
    0.07
     putas
    0.07
    มà¸Ń
    0.07
    AdapterManager
    0.07
     molec
    0.07
     “[
    0.06
    ARGIN
    0.06
    rž
    0.06
     ï½ľ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.