© 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. 12085
    Prev
    Next
    INDEX
    Explanations

    references to cultural or regional identities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    ãģ®ãĤĤ
    -0.16
    .INSTANCE
    -0.15
    afs
    -0.14
     aynı
    -0.14
    ÅĤad
    -0.14
    recio
    -0.14
    SAME
    -0.14
    ิà¸Ĭ
    -0.14
    entions
    -0.13
    oms
    -0.13
    POSITIVE LOGITS
     as
    0.75
     как
    0.35
     καθÏİÏĤ
    0.34
     als
    0.30
    	as
    0.30
     sebagai
    0.28
     too
    0.26
     以
    0.25
     ainsi
    0.24
     jako
    0.24
    Activations Density 0.030%

    No Known Activations