© 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. 12403
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" and variations indicating speech or claims

    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
    ongyang
    -0.19
    orsi
    -0.14
    ÄĻ
    -0.13
    ÃŃcio
    -0.13
    esome
    -0.13
    azon
    -0.12
    apot
    -0.12
    chl
    -0.12
     quali
    -0.12
    zac
    -0.12
    POSITIVE LOGITS
     that
    0.36
    that
    0.30
     rằng
    0.28
     they
    0.26
     bahwa
    0.21
     repeatedly
    0.21
     ÑĩÑĤо
    0.20
     że
    0.20
    	that
    0.20
     goodbye
    0.20
    Activations Density 0.199%

    No Known Activations