© 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. 92935
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts, indicating an emphasis on specificity within the text

    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
    ÑĥÑĢÑģ
    -0.08
    raison
    -0.07
    ÏģÏīν
    -0.07
     samot
    -0.07
    ogle
    -0.06
    wright
    -0.06
    cpt
    -0.06
    аÑĢов
    -0.06
    //[
    -0.06
    fdc
    -0.06
    POSITIVE LOGITS
    course
    0.07
     past
    0.07
     course
    0.07
    ter
    0.07
     interest
    0.07
    ught
    0.07
     magnitude
    0.07
     ilk
    0.07
     concern
    0.07
    ivery
    0.06
    Activations Density 0.059%

    No Known Activations