© 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. 94861
    Prev
    Next
    INDEX
    Explanations

    specific variable identifiers and their properties in code

    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
    áºŃy
    -0.10
    åIJįçĦ¡ãģĹ
    -0.10
    dete
    -0.08
    ÑĪин
    -0.08
    ï¼ģï¼ģ↵↵
    -0.08
    ãģĵãĤĵãģ«
    -0.08
    åĩºåĵģèĢħ
    -0.08
    Stride
    -0.08
    ?↵↵↵↵↵↵
    -0.08
    (æľ¨
    -0.08
    POSITIVE LOGITS
    ;
    0.09
    {
    0.06
    itt
    0.06
    ¤
    0.06
     ,
    0.06
    ,
    0.06
    ann
    0.06
    =
    0.06
    '
    0.06
    ;↵
    0.06
    Activations Density 0.120%

    No Known Activations