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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54145
    Prev
    Next
    INDEX
    Explanations

    phrases related to player evaluations and statistics 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
    ayla
    -0.08
    enden
    -0.07
    ики
    -0.07
    endas
    -0.07
    ä¸Ŀ
    -0.07
    isas
    -0.07
    rescia
    -0.07
    abi
    -0.07
    inia
    -0.07
    ÑĢеж
    -0.07
    POSITIVE LOGITS
     Hodg
    0.06
    /Base
    0.06
     independently
    0.06
    /***************************************************************************↵
    0.06
    wert
    0.06
    à¹Ģสà¸Ļ
    0.06
    Independ
    0.06
    iz
    0.06
    ноÑĩ
    0.06
    veled
    0.06
    Activations Density 0.018%

    No Known Activations