© 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. 85249
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal citations in court documents, characterized by case names followed by volume numbers, reporter abbreviations, page numbers, and often court/year information in parentheses.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    âĢ¦↵
    -0.12
    ..↵
    -0.12
    Âłin
    -0.11
    <|end_of_text|>
    -0.09
    ...↵
    -0.09
    -fontawesome
    -0.09
    ÙĪاء
    -0.08
     Particularly
    -0.07
     MediaQuery
    -0.07
     âĢ¦↵
    -0.07
    POSITIVE LOGITS
    #ad
    0.15
    .DropDown
    0.15
    _________________↵↵
    0.14
    .Dictionary
    0.14
    .Reporting
    0.14
    #ac
    0.14
    екаÑĢ
    0.14
    Æ¡
    0.14
    #ab
    0.14
    .Serial
    0.14
    Activations Density 0.896%

    No Known Activations