© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    references to travel and transportation details

    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
    yp
    -0.06
    inox
    -0.06
    å¤Ħ
    -0.06
     Parkinson
    -0.06
    846
    -0.06
    gee
    -0.06
    /memory
    -0.06
    venta
    -0.06
    ÑĢин
    -0.06
     handed
    -0.06
    POSITIVE LOGITS
     travel
    0.18
     Travel
    0.15
    Travel
    0.15
    travel
    0.15
     plane
    0.13
    _travel
    0.13
     traveling
    0.12
     travelling
    0.12
     traveled
    0.12
     flights
    0.11
    Activations Density 0.153%

    No Known Activations