© 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. 99259
    Prev
    Next
    INDEX
    Explanations

    references to youth culture and playful expressions of identity

    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
    ÑĤÑĢо
    -0.07
    tuk
    -0.07
    quo
    -0.07
    andes
    -0.07
    quat
    -0.07
    ebo
    -0.07
     createSelector
    -0.07
    vak
    -0.07
    pras
    -0.07
    ava
    -0.07
    POSITIVE LOGITS
     tender
    0.06
    idel
    0.06
    ุà¹ī
    0.06
    ameleon
    0.06
    üss
    0.06
     recursion
    0.05
    á»ĩ
    0.05
    ابت
    0.05
    ãĥ¼ãĥį
    0.05
     Dexter
    0.05
    Activations Density 0.002%

    No Known Activations