© 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. 30352
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions used in programming

    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
    alf
    -0.07
    ë¹
    -0.06
    òng
    -0.06
    essen
    -0.06
    quarter
    -0.06
     Tart
    -0.06
     Quarter
    -0.06
    ɵ
    -0.06
    ãģĵãģ¨
    -0.06
    اعة
    -0.06
    POSITIVE LOGITS
    ()[
    0.10
    ')[
    0.08
    ")[
    0.08
    AndGet
    0.08
    )[
    0.07
    [][
    0.07
    ))[
    0.07
    FileSync
    0.07
     Lars
    0.07
    urette
    0.06
    Activations Density 0.020%

    No Known Activations