© 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. 21894
    Prev
    Next
    INDEX
    Explanations

    items that indicate a structured sequence or hierarchy

    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
    /ch
    -0.17
     ydk
    -0.16
    Îŀ
    -0.15
    ertino
    -0.15
    ocha
    -0.15
    è±
    -0.15
    /cop
    -0.15
    CHAN
    -0.15
     ÐļÑĢи
    -0.14
    /cal
    -0.14
    POSITIVE LOGITS
    _C
    0.33
     c
    0.30
    -C
    0.28
    _c
    0.28
    	C
    0.27
    -c
    0.26
     C
    0.26
    .C
    0.26
    	c
    0.25
    ÂłC
    0.24
    Activations Density 0.375%

    No Known Activations