© 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. 63132
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and layout attributes

    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
    pez
    -0.08
    ADING
    -0.08
    intree
    -0.07
    kos
    -0.07
    ebe
    -0.07
    dash
    -0.07
    /head
    -0.07
     Göz
    -0.07
     Ãľst
    -0.07
    getDisplay
    -0.06
    POSITIVE LOGITS
     FloatingActionButton
    0.08
     fab
    0.07
     icon
    0.06
    ÙĪرد
    0.06
     Icon
    0.06
     camer
    0.06
     New
    0.06
     Ves
    0.06
     distance
    0.06
     distances
    0.06
    Activations Density 0.001%

    No Known Activations