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

    Neuronpedia

    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. 78969
    Prev
    Next
    INDEX
    Explanations

    references to sheets, likely indicating formats or documents related to data

    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
    ic
    -0.07
    frei
    -0.07
    íĴį
    -0.06
    yny
    -0.06
    _charset
    -0.06
     ÑĢаÑģп
    -0.06
     attend
    -0.06
    alf
    -0.06
    gran
    -0.06
    iji
    -0.06
    POSITIVE LOGITS
    uyo
    0.07
    roperty
    0.07
    worm
    0.07
    ulur
    0.07
    ugar
    0.07
    owel
    0.06
    .Persistent
    0.06
    ossible
    0.06
    ÙİÙĨ
    0.06
    anguages
    0.06
    Activations Density 0.005%

    No Known Activations