© 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. 69116
    Prev
    Next
    INDEX
    Explanations

    dates and events related to technology conferences

    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
     crowdfunding
    -0.06
     ec
    -0.06
     circulated
    -0.06
     ÙĪاس
    -0.06
     multiplic
    -0.06
    ip
    -0.05
    ÏĦα
    -0.05
     gent
    -0.05
     circ
    -0.05
     uniform
    -0.05
    POSITIVE LOGITS
     sesso
    0.08
     ApplicationException
    0.07
    _sess
    0.07
    idot
    0.07
    شد
    0.07
    .Glide
    0.07
     evangel
    0.07
    EventData
    0.07
    .mx
    0.06
    ê³Ħ
    0.06
    Activations Density 0.012%

    No Known Activations