© 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. 44988
    Prev
    Next
    INDEX
    Explanations

    variations of the word "bio" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĭ
    -0.16
    enci
    -0.16
    bk
    -0.16
    ivan
    -0.15
    ÙĢ
    -0.15
    bpp
    -0.15
     purse
    -0.15
    าว
    -0.15
    uy
    -0.14
    ia
    -0.14
    POSITIVE LOGITS
    well
    0.20
    iction
    0.20
    rom
    0.19
    ubs
    0.17
    tails
    0.17
    weep
    0.17
    rome
    0.17
    extr
    0.16
    ood
    0.16
     Trafford
    0.16
    Activations Density 0.101%

    No Known Activations