© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94588
    Prev
    Next
    INDEX
    Explanations

    references to motorsports events and their associated details

    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
    oles
    -0.07
    IEL
    -0.07
     closures
    -0.06
    okt
    -0.06
     Closure
    -0.06
     Engl
    -0.06
     instr
    -0.06
     Kore
    -0.06
    à¸Ļะ
    -0.06
    flater
    -0.06
    POSITIVE LOGITS
    áŀ¶
    0.08
    uci
    0.07
    ви
    0.07
    ardu
    0.06
    yr
    0.06
    olk
    0.06
    à¤Łà¤ķ
    0.06
     Volk
    0.06
    PointerException
    0.06
    AMED
    0.06
    Activations Density 0.001%

    No Known Activations