© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 85267
    Prev
    Next
    INDEX
    Explanations

    attributes and properties related to HTML elements in a script

    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
     tiener
    -0.07
    osl
    -0.07
    .HttpContext
    -0.07
    pek
    -0.07
     hete
    -0.07
    iske
    -0.07
    OfSize
    -0.07
    ãĥ©ãĤ¹
    -0.07
    GINE
    -0.07
     seins
    -0.07
    POSITIVE LOGITS
     rel
    0.09
    src
    0.07
     href
    0.07
    href
    0.06
     src
    0.06
    alt
    0.06
     class
    0.06
    ¢°
    0.06
     alt
    0.06
    avn
    0.06
    Activations Density 0.055%

    No Known Activations