© 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. 15-LLAMASCOPE-RES-131K
    11. 85991
    Prev
    Next
    INDEX
    Explanations

    terms related to gambling and gaming contexts

    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
    ynos
    -0.07
    rex
    -0.07
    eldo
    -0.07
    lech
    -0.06
    ventus
    -0.06
     Dummy
    -0.06
    bbing
    -0.06
    ÑĪки
    -0.06
    irs
    -0.06
    gage
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
     progressive
    0.07
    [--
    0.06
    /includes
    0.06
     dejtingsaj
    0.06
    Sequential
    0.06
    éļ
    0.06
    SpaceItem
    0.06
     carb
    0.06
    papers
    0.06
    Activations Density 0.006%

    No Known Activations