© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106196
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction and positive feedback about design work

    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
    ynet
    -0.07
    umm
    -0.07
    ège
    -0.07
    еÑĦ
    -0.07
    اÙħÛĮÙĨ
    -0.07
    enheim
    -0.07
    enek
    -0.07
    Æ¡
    -0.07
    bject
    -0.07
    Ñij
    -0.07
    POSITIVE LOGITS
     final
    0.07
     contest
    0.07
     design
    0.07
    final
    0.06
     ìĿij
    0.06
    649
    0.06
     finals
    0.06
     Final
    0.06
     feedback
    0.06
     respond
    0.06
    Activations Density 0.004%

    No Known Activations