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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8816
    Prev
    Next
    INDEX
    Explanations

    specific components and issues related to mechanical assemblies and firearms

    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
    CHIP
    -0.17
    imas
    -0.15
    gger
    -0.14
    ouz
    -0.14
    usercontent
    -0.14
     au
    -0.13
    UCH
    -0.13
    ingen
    -0.13
    .toolbox
    -0.13
    наÑĢÑĥж
    -0.13
    POSITIVE LOGITS
     assembly
    0.33
     Assembly
    0.28
     assemblies
    0.27
    assembly
    0.25
    Assembly
    0.21
    alone
    0.21
    -equipped
    0.21
    (s
    0.19
    less
    0.18
    -less
    0.18
    Activations Density 0.249%

    No Known Activations