© 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. 33224
    Prev
    Next
    INDEX
    Explanations

    activities or states that involve motion or action

    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
    ings
    -0.30
    /remove
    -0.25
    le
    -0.22
    ÂŃing
    -0.20
    INGS
    -0.19
    /write
    -0.19
    lei
    -0.17
    ers
    -0.17
    ify
    -0.17
    site
    -0.17
    POSITIVE LOGITS
    redient
    0.27
    ame
    0.26
    redients
    0.26
    ness
    0.24
    enuity
    0.23
    AME
    0.21
     spree
    0.20
    REDIENT
    0.20
    reen
    0.19
    tons
    0.18
    Activations Density 0.181%

    No Known Activations