© 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. 17-LLAMASCOPE-RES-131K
    11. 39637
    Prev
    Next
    INDEX
    Explanations

    elements related to competitive events, particularly in the context of wrestling matches

    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
     Starter
    -0.06
    amon
    -0.06
    illac
    -0.06
     Châu
    -0.06
     especially
    -0.06
     frost
    -0.06
    ryn
    -0.06
     !***
    -0.06
    uci
    -0.06
    åIJ¾
    -0.05
    POSITIVE LOGITS
     GAM
    0.06
    élé
    0.06
     Wilhelm
    0.06
    ÏĥÏĦα
    0.06
    sonian
    0.06
    SEL
    0.06
    Trademark
    0.06
    ÏĢον
    0.06
    Slides
    0.06
     Witnesses
    0.06
    Activations Density 0.003%

    No Known Activations