© 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 EvalsExportsAPI 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. 29030
    Prev
    Next
    INDEX
    Explanations

    references to transportation methods and related travel logistics

    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
    иÑĨ
    -0.06
    innie
    -0.06
     Gül
    -0.06
    ienda
    -0.06
    urga
    -0.05
    nám
    -0.05
    ware
    -0.05
    rupa
    -0.05
    enger
    -0.05
     fmt
    -0.05
    POSITIVE LOGITS
    çıŃ
    0.07
     schedules
    0.07
     schedule
    0.07
     ride
    0.07
    ogan
    0.06
     spoleÄįnosti
    0.06
    pent
    0.06
     å¸
    0.06
     Schedule
    0.06
    ieri
    0.06
    Activations Density 0.092%

    No Known Activations