© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 45188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     undermin
    -0.16
    loub
    -0.15
    ãĤĮãģ©
    -0.15
    sian
    -0.14
     escorte
    -0.14
    adele
    -0.14
    nila
    -0.14
    .MixedReality
    -0.14
     overposting
    -0.14
    _perms
    -0.14
    POSITIVE LOGITS
     or
    0.16
    Ã
    0.15
    âĢ¦↵
    0.14
    ÃŃ
    0.14
    ieri
    0.14
    -g
    0.14
     ÙħØ«ÙĦا
    0.14
    ¬
    0.13
    опÑĢи
    0.13
    âĢ¦↵↵
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.