© 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. 45039
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating transformation or change

    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
    ymes
    -0.16
    alet
    -0.15
    pag
    -0.13
    à¸Ńย
    -0.13
    acia
    -0.13
    KF
    -0.13
    Įĵ
    -0.13
    Ø«ÙĦ
    -0.13
    ppe
    -0.13
    Pag
    -0.12
    POSITIVE LOGITS
     possible
    1.04
    possible
    0.88
     Possible
    0.87
     posible
    0.81
    Possible
    0.81
     possibile
    0.80
     possibility
    0.75
     possÃŃvel
    0.71
    _possible
    0.71
     POSS
    0.69
    Activations Density 0.042%

    No Known Activations