© 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. 5988
    Prev
    Next
    INDEX
    Explanations

    specific records related to competitive sports events

    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
    itzer
    -0.10
    ë²Į
    -0.08
    ÃŃÅĻ
    -0.08
    competition
    -0.08
    eldon
    -0.08
    haar
    -0.08
    DRV
    -0.07
    breadcrumbs
    -0.07
    ERRU
    -0.07
    çħĻ
    -0.07
    POSITIVE LOGITS
    aren
    0.06
     hal
    0.06
    ass
    0.06
     toy
    0.05
    arel
    0.05
    ,
    0.05
     toys
    0.05
    bag
    0.05
     fert
    0.05
    ùa
    0.05
    Activations Density 0.013%

    No Known Activations