© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53713
    Prev
    Next
    INDEX
    Explanations

    numerical values and phrases related to betting or gaming statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    à¸Ľà¸¥
    -0.07
     bow
    -0.07
    etto
    -0.07
    chwitz
    -0.07
     urban
    -0.07
     acomp
    -0.06
    etten
    -0.06
    æ®
    -0.06
    Attachments
    -0.06
     Albert
    -0.06
    POSITIVE LOGITS
    iram
    0.07
    rens
    0.06
     server
    0.06
     laundering
    0.06
     Steam
    0.06
    horia
    0.06
     Server
    0.06
    dej
    0.06
    ency
    0.06
    idan
    0.06
    Activations Density 0.001%

    No Known Activations