© 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. 127636
    Prev
    Next
    INDEX
    Explanations

    terms related to baseball statistics and 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
    á»ĵng
    -0.07
    orthy
    -0.07
     former
    -0.06
     ex
    -0.06
    ily
    -0.06
     currently
    -0.06
     current
    -0.06
    sburg
    -0.06
     Former
    -0.06
    currently
    -0.06
    POSITIVE LOGITS
     gider
    0.07
    -parse
    0.07
    urai
    0.07
    _almost
    0.07
    anch
    0.06
     largo
    0.06
    .sul
    0.06
    æ´
    0.06
     Deng
    0.06
    xee
    0.06
    Activations Density 0.000%

    No Known Activations