© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    patterns or formats related to structured data or code

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

    Technical syntax elements appearing across different programming languages, markup formats like LaTeX, and structured document formatting.

    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
    avia
    -0.07
    aze
    -0.06
     unre
    -0.06
    ulet
    -0.06
    .I
    -0.06
    ाध
    -0.06
    -
    -0.06
    angi
    -0.05
    _ARROW
    -0.05
    lamaya
    -0.05
    POSITIVE LOGITS
    (disposing
    0.10
    0.07
     queryInterface
    0.07
     pornstar
    0.07
     gezocht
    0.07
    macen
    0.07
    yscale
    0.07
    .mybatisplus
    0.07
    obuf
    0.06
    rado
    0.06
    Activations Density 0.137%

    No Known Activations