© 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. 84443
    Prev
    Next
    INDEX
    Explanations

    commands related to turning devices off or shutting down systems

    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
    enu
    -0.07
    malink
    -0.07
    eil
    -0.07
    dana
    -0.07
    DefaultValue
    -0.06
    Ñĩай
    -0.06
     initialValue
    -0.06
     fill
    -0.06
    fill
    -0.06
    çĿĢ
    -0.06
    POSITIVE LOGITS
    ">ÃĹ</
    0.07
     khá»ıi
    0.07
    /close
    0.07
    (close
    0.06
    icas
    0.06
    æİī
    0.06
    urgeon
    0.06
    WithError
    0.06
    zcze
    0.06
    SelectionMode
    0.06
    Activations Density 0.012%

    No Known Activations