© 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. 94230
    Prev
    Next
    INDEX
    Explanations

    instances of email addresses

    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
    allis
    -0.07
    kick
    -0.07
    ara
    -0.07
    érc
    -0.07
    heim
    -0.07
    rey
    -0.06
    coon
    -0.06
    kee
    -0.06
    elow
    -0.06
    poses
    -0.06
    POSITIVE LOGITS
     toReturn
    0.07
    .Companion
    0.07
     Deferred
    0.07
    implify
    0.06
     Monroe
    0.06
    òa
    0.06
     civ
    0.06
    é³¥
    0.06
     *__
    0.06
    classifier
    0.06
    Activations Density 0.003%

    No Known Activations