© 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 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. 17-LLAMASCOPE-RES-131K
    11. 131001
    Prev
    Next
    INDEX
    Explanations

    events occurring in a sports context, particularly focusing on game actions and 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
    cope
    -0.07
    ivol
    -0.07
    ç¹ģ
    -0.06
    ë¯
    -0.06
    resco
    -0.06
     addictive
    -0.06
    esch
    -0.06
    thumb
    -0.06
     sublicense
    -0.06
    Formula
    -0.06
    POSITIVE LOGITS
     Soccer
    0.09
     soccer
    0.09
    occer
    0.08
     goals
    0.08
     goal
    0.08
     Goal
    0.07
    /go
    0.07
     Goals
    0.07
    _goal
    0.07
     MLS
    0.07
    Activations Density 0.052%

    No Known Activations