© 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. 70738
    Prev
    Next
    INDEX
    Explanations

    syntax elements and formatting commands within text

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

    Paragraph breaks in LaTeX typesetting, often appearing as "\par" followed by a new line or "\noindent" commands that control text formatting and spacing in academic/mathematical documents.

    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
    ullet
    -0.07
    elli
    -0.07
     latter
    -0.07
    ÃŃch
    -0.07
    entially
    -0.06
    RIPTION
    -0.06
    ramer
    -0.06
    bbbb
    -0.06
    ARGIN
    -0.06
     Butt
    -0.06
    POSITIVE LOGITS
    _cmos
    0.07
    /apis
    0.06
    Ậ
    0.06
    ÌĨ
    0.06
    -Identifier
    0.06
     pros
    0.06
    807
    0.06
    537
    0.06
    +-+-+-+-+-+-+-+-
    0.06
    åľ
    0.06
    Activations Density 0.072%

    No Known Activations