© 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. 26195
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their political affiliations or demographics

    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
    polator
    -0.16
    ataire
    -0.15
    á»ı
    -0.14
    виÑī
    -0.14
    inka
    -0.14
    CLI
    -0.14
    ungle
    -0.14
    ascus
    -0.14
    üstü
    -0.14
    Ø´ÙĨ
    -0.13
    POSITIVE LOGITS
     Tucson
    0.48
    ucson
    0.39
     Arizona
    0.29
    Arizona
    0.26
     Sah
    0.26
     UA
    0.24
     desert
    0.23
    @email
    0.23
     Desert
    0.22
    -UA
    0.22
    Activations Density 0.017%

    No Known Activations