© 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. 59728
    Prev
    Next
    INDEX
    Explanations

    input fields and related HTML elements in web development contexts

    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
    ´Ŀ
    -0.07
     pur
    -0.06
    ertz
    -0.06
    hea
    -0.06
    Ñıб
    -0.06
    abei
    -0.06
     AppModule
    -0.06
    ular
    -0.06
     bubble
    -0.06
    ckett
    -0.06
    POSITIVE LOGITS
     výbÄĽ
    0.08
     OpenFileDialog
    0.08
    anko
    0.08
    _Selection
    0.08
     selecting
    0.08
     select
    0.08
     sele
    0.08
    /select
    0.07
     selects
    0.07
    select
    0.07
    Activations Density 0.011%

    No Known Activations