© 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. 58368
    Prev
    Next
    INDEX
    Explanations

    phrases related to operations or processes involving transportation or 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
     currently
    -0.08
     Currently
    -0.07
    currently
    -0.07
     presently
    -0.07
    .fm
    -0.06
     mechanic
    -0.06
    ussy
    -0.06
    vell
    -0.06
    ansi
    -0.06
    WindowState
    -0.06
    POSITIVE LOGITS
    eway
    0.07
     Haz
    0.07
    adero
    0.06
    UTTON
    0.06
     Tarif
    0.06
    ī´
    0.06
    ssp
    0.06
    åģľ
    0.06
     Sund
    0.06
     Camb
    0.06
    Activations Density 0.014%

    No Known Activations