© 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. 43950
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and engagement with 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
     myself
    -0.27
     anyone
    -0.23
     yourself
    -0.22
     everyone
    -0.20
    大家
    -0.19
    人们
    -0.17
     people
    -0.17
    everyone
    -0.17
     anybody
    -0.16
     oneself
    -0.16
    POSITIVE LOGITS
     themselves
    0.45
     their
    0.26
     leurs
    0.24
     Their
    0.23
    ï¼Įä»ĸ们
    0.23
    Their
    0.23
    ä»ĸ们
    0.22
     THEIR
    0.22
     há»į
    0.21
    their
    0.21
    Activations Density 0.054%

    No Known Activations