© 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. 54707
    Prev
    Next
    INDEX
    Explanations

    logistical details related to travel and transportation

    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
    icum
    -0.08
    ayo
    -0.07
    umo
    -0.07
    Opening
    -0.07
    .pkg
    -0.07
    idlo
    -0.06
    urgeon
    -0.06
    ple
    -0.06
    ÑĢади
    -0.06
    «ĺ
    -0.06
    POSITIVE LOGITS
     departure
    0.10
     final
    0.09
     depart
    0.09
     farewell
    0.09
     exit
    0.09
     Depart
    0.09
     leaving
    0.08
    Depart
    0.08
     return
    0.08
    exit
    0.08
    Activations Density 0.020%

    No Known Activations