© 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. 15-LLAMASCOPE-RES-131K
    11. 103438
    Prev
    Next
    INDEX
    Explanations

    elements related to sports scheduling and competition

    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
    लà¤Ĺ
    -0.07
    OwnProperty
    -0.07
     ATTRIBUTE
    -0.06
     accessed
    -0.06
     IReadOnly
    -0.06
    ournal
    -0.06
    eshire
    -0.06
     Suspension
    -0.06
    _CN
    -0.06
     पह
    -0.06
    POSITIVE LOGITS
     meg
    0.07
     annual
    0.07
    /target
    0.07
    631
    0.07
     gaz
    0.07
     annually
    0.07
     Annual
    0.07
     schedule
    0.06
     Schedule
    0.06
    Ĥæķ°
    0.06
    Activations Density 0.002%

    No Known Activations