© 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. 26843
    Prev
    Next
    INDEX
    Explanations

    layout-related attributes in code, particularly for Android or UI design

    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
    olt
    -0.07
    ubern
    -0.07
    ico
    -0.06
    èo
    -0.06
    ãĥ¼ãĥĹ
    -0.06
    velle
    -0.06
    idel
    -0.06
    ligt
    -0.06
    thy
    -0.06
    elight
    -0.06
    POSITIVE LOGITS
    kowski
    0.07
    kea
    0.07
    zione
    0.06
    789
    0.06
    ATUS
    0.06
     acomp
    0.06
    одаÑĢ
    0.06
    558
    0.06
     Hawkins
    0.06
    atte
    0.06
    Activations Density 0.001%

    No Known Activations