© 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. 28694
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS element attributes related to stylesheets and links

    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
    591
    -0.07
    atches
    -0.06
    ope
    -0.06
    sembles
    -0.06
    lem
    -0.06
    udes
    -0.06
    ioned
    -0.06
    rippling
    -0.06
    bons
    -0.06
    ARCHAR
    -0.06
    POSITIVE LOGITS
    .skin
    0.07
    .Must
    0.07
    .bundle
    0.07
    _mA
    0.07
     fragment
    0.06
    undle
    0.06
    Bundle
    0.06
    ÏĦολ
    0.06
    atego
    0.06
    .CSS
    0.06
    Activations Density 0.004%

    No Known Activations