© 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. 90510
    Prev
    Next
    INDEX
    Explanations

    aspects related to attendance and crowd size at 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
    allet
    -0.07
     fur
    -0.06
     presently
    -0.06
    ippi
    -0.06
     ÎĶε
    -0.06
     Portfolio
    -0.06
    PTS
    -0.06
     Menu
    -0.06
    Ñij
    -0.06
    Ç
    -0.06
    POSITIVE LOGITS
     attendance
    0.08
     Attendance
    0.07
    Attendance
    0.07
     estimation
    0.07
     numbers
    0.07
    attendance
    0.07
     cif
    0.07
    numbers
    0.07
    usize
    0.06
     estimate
    0.06
    Activations Density 0.017%

    No Known Activations