© 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. 40322
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly of individuals, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ëį°ìĿ´íĬ¸
    -0.09
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.09
    ëĶĶìĭľ
    -0.08
    .appspot
    -0.08
    ToPoint
    -0.07
    InSection
    -0.07
    /goto
    -0.07
    ë³´ëĤ´ê¸°
    -0.07
     predecess
    -0.07
    ,},↵
    -0.07
    POSITIVE LOGITS
    uras
    0.06
    Question
    0.06
    ’s
    0.06
     himself
    0.05
    [
    0.05
     ray
    0.05
    ye
    0.05
    dorf
    0.05
     Sol
    0.05
    heim
    0.05
    Activations Density 0.018%

    No Known Activations