© 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. 26952
    Prev
    Next
    INDEX
    Explanations

    tokens related to data structure definitions or programming constructs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    опол
    -0.07
     nouve
    -0.07
    Äģn
    -0.07
    ardash
    -0.06
     å®
    -0.06
    zÄħd
    -0.06
     Sherman
    -0.06
    оÑĩек
    -0.06
    ator
    -0.06
    ìŀ¥ìĿĦ
    -0.06
    POSITIVE LOGITS
     fifth
    0.09
    -five
    0.09
    5
    0.09
     five
    0.09
     Fifth
    0.08
    Ù¥
    0.08
    five
    0.08
     Five
    0.08
     cinco
    0.07
    äºĶ
    0.07
    Activations Density 0.106%

    No Known Activations