© 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. 129289
    Prev
    Next
    INDEX
    Explanations

    words associated with crime and law enforcement

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

    Fragments of technical, scientific, or specialized terminology that appear in context-specific documents, including code snippets, scientific papers, and specialized content.

    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
    [".
    -0.07
    PÅĻÃŃ
    -0.07
    _AG
    -0.07
    'gc
    -0.07
    à¸ķรว
    -0.07
    ìĽIJìĿ´
    -0.07
    Ú©ÙĦ
    -0.06
    _FAULT
    -0.06
    oun
    -0.06
    ìŀ¥ìĿĢ
    -0.06
    POSITIVE LOGITS
    ifold
    0.07
    oster
    0.06
    inton
    0.06
    hazi
    0.06
    sWith
    0.06
    igator
    0.06
     compos
    0.05
    ekler
    0.05
    _equalTo
    0.05
    atrix
    0.05
    Activations Density 0.137%

    No Known Activations