© 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. 17-LLAMASCOPE-RES-131K
    11. 41354
    Prev
    Next
    INDEX
    Explanations

    references to vacation and travel experiences

    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
     ÄĮer
    -0.07
    thane
    -0.07
    alley
    -0.07
    ombres
    -0.07
    acct
    -0.07
    ride
    -0.07
    ragen
    -0.07
     навеÑĢ
    -0.07
    (strpos
    -0.07
    лиÑĪ
    -0.07
    POSITIVE LOGITS
     vacation
    0.16
     holiday
    0.15
     vacations
    0.14
     holidays
    0.13
     resorts
    0.13
     resort
    0.12
    Vac
    0.11
     Vacation
    0.11
     getaway
    0.11
    holiday
    0.11
    Activations Density 0.305%

    No Known Activations