© 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. 89534
    Prev
    Next
    INDEX
    Explanations

    mentions of free or complimentary services and amenities in hospitality contexts

    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
    que
    -0.08
     Erotische
    -0.07
    ibo
    -0.07
    mailto
    -0.07
    GINE
    -0.07
    catid
    -0.07
     нами
    -0.07
    _locs
    -0.07
    REM
    -0.07
    ooter
    -0.06
    POSITIVE LOGITS
     parking
    0.08
     Parking
    0.07
    Parking
    0.07
     Wi
    0.06
    ãĥ¼ãĥĸ
    0.06
    ea
    0.06
     sty
    0.06
    Inflater
    0.06
     Kids
    0.06
     Kid
    0.06
    Activations Density 0.004%

    No Known Activations