© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27352
    Prev
    Next
    INDEX
    Explanations

    references to sports-related terms, specifically involving player statistics and match outcomes

    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
    licer
    -0.09
    swire
    -0.09
    رات
    -0.07
     lez
    -0.07
    Ãłng
    -0.07
    isas
    -0.07
    geber
    -0.07
    ViewItem
    -0.07
    .scalablytyped
    -0.07
    hua
    -0.07
    POSITIVE LOGITS
     ga
    0.05
    mae
    0.05
    à¤Ĥय
    0.05
     Ju
    0.05
     leading
    0.05
     Herman
    0.05
     region
    0.05
     unsur
    0.05
     habit
    0.05
    agus
    0.05
    Activations Density 0.015%

    No Known Activations