© 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. 84966
    Prev
    Next
    INDEX
    Explanations

    references to authors or works of fiction

    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
    oret
    -0.07
    rál
    -0.07
    yne
    -0.07
    ourcem
    -0.07
    imulator
    -0.07
    hog
    -0.07
    -strokes
    -0.07
    alace
    -0.06
    ediÄŁi
    -0.06
    993
    -0.06
    POSITIVE LOGITS
    kan
    0.08
    à¸Ńà¹Ģมร
    0.07
     bur
    0.06
    -Cal
    0.06
     Ø¢ÙħرÛĮکا
    0.06
    ÑĢовиÑĩ
    0.06
    ifornia
    0.06
    ëłĪìĿ´
    0.06
    -American
    0.06
    -placeholder
    0.06
    Activations Density 0.004%

    No Known Activations