© 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. 3446
    Prev
    Next
    INDEX
    Explanations

    code snippets related to shader or graphical programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippet delimiters identifying the start of programming code blocks, often appearing in documentation or source files as string literals that contain programming language syntax.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ä¸ĺ
    -0.09
    eut
    -0.07
    елÑİ
    -0.07
    verse
    -0.07
    reff
    -0.07
    desk
    -0.07
    bose
    -0.06
     зали
    -0.06
    endor
    -0.06
     Desk
    -0.06
    POSITIVE LOGITS
    RootElement
    0.07
     public
    0.07
     typedef
    0.07
    BEGIN
    0.06
     ?><?
    0.06
     void
    0.06
    emon
    0.06
    úng
    0.06
     begin
    0.06
     class
    0.06
    Activations Density 0.136%

    No Known Activations