© 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. 130556
    Prev
    Next
    INDEX
    Explanations

    function and event handling keywords related to user interface programming

    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
    SupportedContent
    -0.09
    OptionsResolver
    -0.07
    æĵ¦
    -0.07
    -lfs
    -0.07
    aba
    -0.07
    antino
    -0.07
    pty
    -0.07
    etimes
    -0.07
    OffsetTable
    -0.07
    oltip
    -0.07
    POSITIVE LOGITS
    /Main
    0.07
    OnUiThread
    0.06
    -safe
    0.06
    rone
    0.06
    afe
    0.06
     Bett
    0.06
     Inside
    0.06
     safe
    0.06
    .dispatch
    0.06
    æ´¾
    0.06
    Activations Density 0.009%

    No Known Activations