© 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. 91653
    Prev
    Next
    INDEX
    Explanations

    the presence of specific syntactic structures, particularly curly braces

    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
     boyunca
    -0.07
    á»Ĩ
    -0.07
    edd
    -0.06
    ženÃŃ
    -0.06
    -esque
    -0.06
    enson
    -0.06
    lix
    -0.06
    Ïĥο
    -0.06
    qh
    -0.06
     [âĢ¦
    -0.06
    POSITIVE LOGITS
    ityEngine
    0.08
    æŁĦ
    0.08
    /umd
    0.07
    inkle
    0.07
    oldem
    0.07
    ponce
    0.07
    okable
    0.07
    .AnchorStyles
    0.07
    wise
    0.07
    gue
    0.06
    Activations Density 0.000%

    No Known Activations