© 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. 17-LLAMASCOPE-RES-131K
    11. 128349
    Prev
    Next
    INDEX
    Explanations

    interactions between players and officials during sports events

    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
    zon
    -0.07
    aln
    -0.07
    _attach
    -0.07
     sque
    -0.07
     veÄįer
    -0.06
    PLL
    -0.06
     newInstance
    -0.06
    /proto
    -0.06
    terra
    -0.06
    oday
    -0.06
    POSITIVE LOGITS
     motion
    0.07
     imaginary
    0.07
     animated
    0.07
    lef
    0.06
     Bench
    0.06
     bench
    0.06
     Arabic
    0.06
     arab
    0.06
     Mö
    0.06
    arg
    0.06
    Activations Density 0.029%

    No Known Activations