© 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. 119278
    Prev
    Next
    INDEX
    Explanations

    references to programming functions, methods, and their usage in 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
     bow
    -0.06
    ESA
    -0.06
     Jacqu
    -0.06
    ghi
    -0.06
     certain
    -0.06
     fitting
    -0.06
    ennis
    -0.06
     till
    -0.06
    -
    -0.06
    iale
    -0.05
    POSITIVE LOGITS
    FIXME
    0.07
    indy
    0.07
    TODO
    0.06
    ernaut
    0.06
    _DDR
    0.06
     Karn
    0.06
    ennen
    0.06
     ÙĨظ
    0.06
    	Use
    0.06
    {@
    0.06
    Activations Density 0.033%

    No Known Activations