© 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. 29389
    Prev
    Next
    INDEX
    Explanations

    function definitions and programming constructs in code snippets

    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
    گاÙĨ
    -0.07
    ¶Į
    -0.07
     Decoration
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.06
    akin
    -0.06
    ardon
    -0.06
    æ£ĭ
    -0.06
    avy
    -0.06
    ãĥ³ãĥĦ
    -0.06
    omit
    -0.06
    POSITIVE LOGITS
    igm
    0.07
    orate
    0.06
    444
    0.06
     NONINFRINGEMENT
    0.06
    reeNode
    0.06
     tou
    0.06
    èĬĤ
    0.06
    ucu
    0.06
    ìĽħ
    0.06
    cia
    0.06
    Activations Density 0.002%

    No Known Activations