© 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. 45087
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic relations and government structures

    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
    dbl
    -0.15
    elf
    -0.15
    δο
    -0.14
    ÑĸÑĩ
    -0.14
     mouseClicked
    -0.14
    abe
    -0.14
    abez
    -0.14
     tiener
    -0.14
    adr
    -0.13
    arcer
    -0.13
    POSITIVE LOGITS
     embassy
    0.64
     emb
    0.63
    Emb
    0.61
     Embassy
    0.60
     Emb
    0.58
    emb
    0.56
     ambassador
    0.54
     Cons
    0.52
     Ambassador
    0.51
    Amb
    0.51
    Activations Density 0.039%

    No Known Activations