© 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. 125915
    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
    uky
    -0.07
    /
    -0.07
     &
    -0.07
    ãģ«ãģ¦
    -0.07
    zÄĻ
    -0.06
     behavior
    -0.06
     as
    -0.06
    (
    -0.06
     native
    -0.06
     /
    -0.05
    POSITIVE LOGITS
    :animated
    0.08
    .alias
    0.07
    ализи
    0.07
    InSection
    0.07
    erez
    0.07
    uhn
    0.07
    à¥Ĥà¤Ĥ
    0.07
    ÑĨеÑĢ
    0.07
    Authenticated
    0.07
    ä»ĭ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.