© 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 EvalsExportsinterp-engineNEWAPI 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. 87507
    Prev
    Next
    INDEX
    Explanations

    references to commission structures in the hospitality industry

    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
     society
    -0.07
     Society
    -0.07
    ÑģÑĤи
    -0.06
     imported
    -0.06
    iên
    -0.06
    shipping
    -0.06
    uze
    -0.06
    æ²»
    -0.06
    ampus
    -0.06
    ãĤĪ
    -0.06
    POSITIVE LOGITS
     Booking
    0.09
     booking
    0.08
     hotel
    0.07
    .middle
    0.07
     bookings
    0.07
     Hotel
    0.07
     Gecko
    0.07
     Lexer
    0.06
    æŀ
    0.06
    Booking
    0.06
    Activations Density 0.008%

    No Known Activations