© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    occurrences of the variable 'e' in function parameters and event handlers 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
    emme
    -0.07
    èĭ
    -0.06
    angered
    -0.06
    .IContainer
    -0.06
    isen
    -0.06
     fold
    -0.06
    lenÃŃ
    -0.06
     Glas
    -0.06
    InBackground
    -0.06
     Jennings
    -0.06
    POSITIVE LOGITS
    LP
    0.07
    hoff
    0.07
    Sense
    0.07
    arded
    0.06
    KG
    0.06
    uai
    0.06
     Guam
    0.06
     ked
    0.06
     Gamb
    0.06
    _KP
    0.06
    Activations Density 0.002%

    No Known Activations