© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 22705
    Prev
    Next
    INDEX
    Explanations

    references to addressing or engaging with an audience

    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
     Their
    -0.22
    Their
    -0.21
    ä»ĸåĢij
    -0.20
     THEIR
    -0.20
    ä»ĸ们
    -0.20
     há»į
    -0.19
     their
    -0.18
     themselves
    -0.18
    their
    -0.18
     loro
    -0.17
    POSITIVE LOGITS
     yourselves
    0.24
     out
    0.20
     alike
    0.16
     remember
    0.16
     hare
    0.15
     who
    0.15
     here
    0.14
    Assignable
    0.14
    who
    0.14
    ingers
    0.14
    Activations Density 0.028%

    No Known Activations