© 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. 89620
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dozen" and related numerical expressions indicating quantity

    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
    abor
    -0.07
     beled
    -0.07
    ãģªãģı
    -0.07
    åĬ¨çĶŁæĪIJ
    -0.07
    ogs
    -0.07
    stateParams
    -0.07
    966
    -0.07
    -transitional
    -0.07
    ï¸ı
    -0.06
    à¸Īำà¸Ļวà¸Ļ
    -0.06
    POSITIVE LOGITS
    ths
    0.09
    naire
    0.08
    -plus
    0.08
    aire
    0.08
    -д
    0.07
    ystone
    0.07
    /e
    0.07
    /all
    0.07
    clerosis
    0.07
     Higgins
    0.07
    Activations Density 0.007%

    No Known Activations