© 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. 28696
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" in various contexts

    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
    lessly
    -0.18
    kar
    -0.18
    makers
    -0.17
    ipeg
    -0.16
    aton
    -0.16
    pling
    -0.16
    ersed
    -0.15
    lining
    -0.15
    705
    -0.15
    ãĤĤãģĹ
    -0.15
    POSITIVE LOGITS
    -profit
    0.23
    iginal
    0.23
    aging
    0.23
    bes
    0.22
    êt
    0.21
    ces
    0.21
    -sale
    0.21
     Hire
    0.21
    geries
    0.21
    ager
    0.20
    Activations Density 0.038%

    No Known Activations