© 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. 58580
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and evaluations

    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
    currently
    -0.09
     currently
    -0.09
     now
    -0.08
    still
    -0.08
    tran
    -0.07
    uhan
    -0.07
    being
    -0.07
     still
    -0.07
    bove
    -0.07
    ISCO
    -0.07
    POSITIVE LOGITS
     lately
    0.14
     since
    0.14
    since
    0.10
     recently
    0.09
     Since
    0.09
    Since
    0.09
    以æĿ¥
    0.08
    _since
    0.08
     ÙħÙĨØ°
    0.07
    ince
    0.07
    Activations Density 0.075%

    No Known Activations