© 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. 16427
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events and analyses in sports contexts

    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
    urai
    -0.08
    _CRC
    -0.07
    pository
    -0.07
    elib
    -0.07
    atsu
    -0.07
    GRES
    -0.07
    ansson
    -0.07
    ovice
    -0.07
    ureau
    -0.07
    loom
    -0.07
    POSITIVE LOGITS
     focus
    0.06
     interesting
    0.06
     closely
    0.06
     attempt
    0.06
     potentially
    0.06
     debut
    0.06
    åĪ·
    0.06
     unload
    0.06
    attempt
    0.06
     pressure
    0.05
    Activations Density 0.015%

    No Known Activations