© 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. 27097
    Prev
    Next
    INDEX
    Explanations

    first-person perspectives and expressions of self-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
    ixe
    -0.08
    нед
    -0.07
    361
    -0.07
    mie
    -0.07
    orem
    -0.06
    ird
    -0.06
    igmoid
    -0.06
    gressor
    -0.06
    639
    -0.06
     nedok
    -0.06
    POSITIVE LOGITS
    readystatechange
    0.07
     ServiceException
    0.06
     bench
    0.06
    ylland
    0.06
    ottes
    0.06
    (predicate
    0.06
    ãĤ¯ãĥĪ
    0.06
    accent
    0.06
     Exist
    0.06
    erase
    0.05
    Activations Density 0.030%

    No Known Activations