© 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. 88774
    Prev
    Next
    INDEX
    Explanations

    references to data structures and functions related to programming or software development

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

    Serial output/printing functions in embedded systems code, particularly in 3D printer firmware. These are methods used for sending debug information, status updates, or responses through a serial interface connection.

    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
    λλ
    -0.06
     Fulton
    -0.06
     treff
    -0.06
    .Invariant
    -0.06
    printStats
    -0.06
    ahat
    -0.06
    ÑĢÑĥб
    -0.06
    weed
    -0.06
    ingroup
    -0.06
    .propTypes
    -0.05
    POSITIVE LOGITS
    ://
    0.09
    alic
    0.07
    ÛĮز
    0.07
    vement
    0.07
    اÙĨÙĬا
    0.07
    ëłĩê²Į
    0.06
    _sdk
    0.06
    ÃŃst
    0.06
    ERIC
    0.06
    ServletResponse
    0.06
    Activations Density 0.019%

    No Known Activations