© 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. 22-LLAMASCOPE-RES-131K
    11. 3641
    Prev
    Next
    INDEX
    Explanations

    terms related to player statistics and injuries in sports

    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
    ibi
    -0.07
    ewise
    -0.07
    -separated
    -0.06
    ogle
    -0.06
    quiring
    -0.06
    wers
    -0.06
    ients
    -0.06
    REQ
    -0.06
    toi
    -0.06
    apa
    -0.06
    POSITIVE LOGITS
     jerseys
    0.07
     Authentic
    0.07
     authentic
    0.07
    .getOwnProperty
    0.07
     jersey
    0.07
    Å¡el
    0.07
    ustom
    0.07
    orida
    0.07
     Womens
    0.07
    erdale
    0.07
    Activations Density 0.017%

    No Known Activations