© 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. 9-LLAMASCOPE-RES-131K
    11. 94156
    Prev
    Next
    INDEX
    Explanations

    string quotation marks and related syntax in code or markup

    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
    tte
    -0.07
     FileMode
    -0.07
    umar
    -0.07
    oley
    -0.07
    ope
    -0.07
    Ùħر
    -0.07
    ienne
    -0.07
    ummings
    -0.07
    hire
    -0.07
    jest
    -0.06
    POSITIVE LOGITS
    ίγ
    0.08
    æīİ
    0.07
    839
    0.06
    Triangles
    0.06
    GLOSS
    0.06
    Smarty
    0.06
     Cran
    0.06
     Shay
    0.06
    _styles
    0.06
    .Mask
    0.06
    Activations Density 0.001%

    No Known Activations