© 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. 89404
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel planning and booking

    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
    andes
    -0.08
     Lunch
    -0.06
    perc
    -0.06
    LOUR
    -0.06
    inta
    -0.06
    [attr
    -0.06
     Maur
    -0.06
    Äįel
    -0.06
    ally
    -0.06
    igg
    -0.06
    POSITIVE LOGITS
     spont
    0.09
     travel
    0.09
     planner
    0.07
     Travel
    0.07
     planning
    0.07
     traveling
    0.07
    jang
    0.07
    travel
    0.07
     air
    0.07
     spontaneous
    0.07
    Activations Density 0.017%

    No Known Activations