© 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. 85464
    Prev
    Next
    INDEX
    Explanations

    jQuery selectors and method calls in JavaScript 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
    RIX
    -0.07
     Duy
    -0.07
    _Callback
    -0.07
    SError
    -0.07
    ëĮĢë¡ľ
    -0.07
    Å¡et
    -0.07
    ãĤıãĤĬ
    -0.07
    tainment
    -0.07
    á»ķ
    -0.06
    plode
    -0.06
    POSITIVE LOGITS
    Ðŀ
    0.07
    A
    0.06
    ona
    0.06
    licted
    0.06
    soever
    0.06
    ly
    0.06
     Armour
    0.06
    .TableLayoutPanel
    0.06
    B
    0.06
    .ToolStrip
    0.06
    Activations Density 0.002%

    No Known Activations