© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121640
    Prev
    Next
    INDEX
    Explanations

    references to accommodations and hospitality options

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Lounge
    -0.06
    ounge
    -0.06
    ëĿ¼ìĿ¸
    -0.06
     carried
    -0.06
    apolis
    -0.06
    礼
    -0.06
     arch
    -0.06
    COME
    -0.06
     Lunch
    -0.06
    kah
    -0.06
    POSITIVE LOGITS
     hotel
    0.14
    otel
    0.13
     hotels
    0.13
     Hotel
    0.12
    hotel
    0.11
     motel
    0.11
     accommodation
    0.11
     beds
    0.10
     Hotels
    0.10
     bed
    0.10
    Activations Density 0.087%

    No Known Activations