© 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. 25373
    Prev
    Next
    INDEX
    Explanations

    references to guides or instructional content related to DIY maintenance and repairs

    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
    arger
    -0.15
     ><?
    -0.13
    нÑĶ
    -0.13
    ked
    -0.13
    ÙģاÙĤ
    -0.13
    acomment
    -0.13
     Synopsis
    -0.13
     Highlights
    -0.13
    hlen
    -0.12
    alytics
    -0.12
    POSITIVE LOGITS
     tips
    0.36
     helpful
    0.31
    tips
    0.31
     advice
    0.30
     guides
    0.28
     resource
    0.28
     guide
    0.28
     useful
    0.28
     Practical
    0.28
     Tips
    0.28
    Activations Density 0.067%

    No Known Activations