© 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. 61072
    Prev
    Next
    INDEX
    Explanations

    instances of the word "write" and related actions in the context of programming or coding

    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
    onta
    -0.07
     Older
    -0.07
    uest
    -0.06
     merit
    -0.06
    oble
    -0.06
    ãģĨãģ¡
    -0.06
    extern
    -0.06
    νο
    -0.06
    extView
    -0.06
     ide
    -0.06
    POSITIVE LOGITS
    resse
    0.07
    pone
    0.07
    ÑĢиÑģÑĤи
    0.07
    ynes
    0.07
    421
    0.06
    ollo
    0.06
    .DependencyInjection
    0.06
    代çłģ
    0.06
    955
    0.06
    _interfaces
    0.06
    Activations Density 0.011%

    No Known Activations