© 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. 57712
    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
    quist
    -0.06
     undo
    -0.06
    ende
    -0.06
    790
    -0.06
     Reb
    -0.06
    ë°Ģ
    -0.06
    kins
    -0.06
     blow
    -0.06
    iciar
    -0.06
    ihan
    -0.06
    POSITIVE LOGITS
     Edgar
    0.06
     جÙĪÙĨ
    0.06
     Mona
    0.06
     envelope
    0.06
    EdgeInsets
    0.06
     ÐĶжон
    0.06
    titleLabel
    0.06
    ÑģÑĤÑĢи
    0.06
    illon
    0.06
     McKay
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.