© 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. 87764
    Prev
    Next
    INDEX
    Explanations

    inquiries about specific products and properties

    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
     ÙħÙĪب
    -0.08
     endregion
    -0.08
    taire
    -0.07
    aring
    -0.07
    ắn
    -0.07
    ÙĪÙĦد
    -0.07
    Ãłu
    -0.07
    anes
    -0.06
    ntl
    -0.06
    ton
    -0.06
    POSITIVE LOGITS
     particular
    0.08
     specific
    0.08
     featured
    0.07
     Erk
    0.07
     products
    0.06
     available
    0.06
    _AVAILABLE
    0.06
    eyse
    0.06
     Raum
    0.06
    featured
    0.06
    Activations Density 0.015%

    No Known Activations