© 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. 17260
    Prev
    Next
    INDEX
    Explanations

    terms related to the hospitality industry and hotel management

    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
    reta
    -0.06
    nox
    -0.06
    evin
    -0.06
    pedia
    -0.06
    eldom
    -0.06
     dire
    -0.06
    iver
    -0.06
    asar
    -0.06
     utilization
    -0.05
    idon
    -0.05
    POSITIVE LOGITS
    ALLED
    0.07
    alsex
    0.07
     nackte
    0.07
    ONTAL
    0.07
     NONINFRINGEMENT
    0.07
     suche
    0.07
     spiele
    0.07
    Ñĩки
    0.07
     franchises
    0.07
    _sdk
    0.07
    Activations Density 0.010%

    No Known Activations