© 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. 99274
    Prev
    Next
    INDEX
    Explanations

    references to labels and labeling in code or documents

    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
    ling
    -0.08
    itag
    -0.07
    iks
    -0.07
    cop
    -0.06
    ite
    -0.06
    .Toolkit
    -0.06
     ÙħÛĮÙĦادÛĮ
    -0.06
    èIJ½
    -0.06
    aid
    -0.06
    uga
    -0.06
    POSITIVE LOGITS
    inalg
    0.07
    xffffff
    0.07
    æ³¥
    0.07
    antee
    0.06
    abyrinth
    0.06
    coration
    0.06
    -IS
    0.06
    postcode
    0.06
    GenerationStrategy
    0.06
     Fowler
    0.06
    Activations Density 0.011%

    No Known Activations