© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25185
    Prev
    Next
    INDEX
    Explanations

    references to guides or instructional content

    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
    resh
    -0.12
    oret
    -0.12
    dea
    -0.12
    phem
    -0.12
    iming
    -0.11
    issing
    -0.11
     omas
    -0.11
    aug
    -0.11
    mvc
    -0.11
    åĿª
    -0.11
    POSITIVE LOGITS
     next
    0.32
     previous
    0.28
     above
    0.28
     following
    0.27
     below
    0.27
     last
    0.24
     section
    0.23
    next
    0.23
     linked
    0.23
     earlier
    0.22
    Activations Density 0.316%

    No Known Activations