© 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. 126007
    Prev
    Next
    INDEX
    Explanations

    behaviors and interactions among animals in their environment

    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
     fingert
    -0.07
    ktor
    -0.07
     mileage
    -0.07
    ırak
    -0.06
    bz
    -0.06
     Jak
    -0.06
    Äĥm
    -0.06
    Suppress
    -0.06
    umper
    -0.06
    _EXPORT
    -0.06
    POSITIVE LOGITS
     Animalia
    0.07
     discrimin
    0.07
    رÛĮÙĤ
    0.06
     ÑĢаÑģÑĩ
    0.06
    .mozilla
    0.06
    ê
    0.06
    loff
    0.06
     entr
    0.06
    /******/
    0.06
    odesk
    0.06
    Activations Density 0.007%

    No Known Activations