© 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. 27759
    Prev
    Next
    INDEX
    Explanations

    terms related to movement or transportation contexts

    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
     our
    -0.06
    TK
    -0.06
     simply
    -0.06
     [...]
    -0.06
    овеÑĢ
    -0.06
     Gew
    -0.06
     faithfully
    -0.05
    exit
    -0.05
     Mans
    -0.05
     tempered
    -0.05
    POSITIVE LOGITS
    ilogy
    0.07
    (æĹ¥
    0.07
    \Id
    0.07
    getWindow
    0.07
    Caption
    0.07
    cene
    0.07
    едини
    0.07
    ARIO
    0.06
     çeÅŁitli
    0.06
    åŃĹå¹ķ
    0.06
    Activations Density 0.001%

    No Known Activations