© 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. 15-LLAMASCOPE-RES-131K
    11. 89577
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structural elements in programming languages

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

    Programming language syntax elements, particularly variable names, function calls, operators, and delimiters that appear in code blocks across various programming languages and markup formats (C++, PHP, LaTeX, HTML).

    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
    omik
    -0.07
    ноÑģи
    -0.07
    ÑĪки
    -0.07
    ipop
    -0.07
    loff
    -0.07
    мени
    -0.07
    ắc
    -0.07
    ÑĢави
    -0.07
    oses
    -0.07
    hdr
    -0.07
    POSITIVE LOGITS
    ammers
    0.05
     ph
    0.05
    æĭŁ
    0.05
    .biz
    0.05
    HN
    0.05
     Schn
    0.05
     Keith
    0.05
     particular
    0.05
     Nigel
    0.05
    &apos
    0.05
    Activations Density 0.095%

    No Known Activations