© 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. 55257
    Prev
    Next
    INDEX
    Explanations

    code-related patterns and programming constructs

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

    Code block closures like closing braces, parentheses, brackets or tags at the end of code snippets, often followed by or preceding some form of punctuation or line break.

    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
    èĿ
    -0.07
    yz
    -0.06
    esModule
    -0.06
    angu
    -0.06
    åĽ
    -0.06
    ayi
    -0.06
    صر
    -0.06
    éĢĥ
    -0.06
     Alman
    -0.06
    imax
    -0.06
    POSITIVE LOGITS
     answer
    0.07
     answers
    0.07
     Answer
    0.07
     answered
    0.07
     ANSW
    0.07
    Answer
    0.07
    ÃĸL
    0.06
    ITTE
    0.06
     dna
    0.06
    .д
    0.06
    Activations Density 0.003%

    No Known Activations