© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91588
    Prev
    Next
    INDEX
    Explanations

    computer programming constructs and HTML content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Programming code elements where special characters or keywords denote string literals, variable declarations, or code templates - often shown with variable assignment and string content, especially in shader programming or HTML/code generation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    FTP
    -0.06
    HIP
    -0.06
     NH
    -0.06
    abis
    -0.06
     buds
    -0.06
    SSL
    -0.06
     Dub
    -0.06
    лиÑĤ
    -0.05
    esser
    -0.05
     picks
    -0.05
    POSITIVE LOGITS
     body
    0.09
    unal
    0.09
    textarea
    0.09
     BODY
    0.09
    BODY
    0.08
     contents
    0.08
    usercontent
    0.08
    .body
    0.08
    body
    0.08
    contents
    0.08
    Activations Density 0.159%

    No Known Activations