© 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. 15041
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after."

    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
     after
    -0.36
    after
    -0.27
     AFTER
    -0.25
     After
    -0.25
     después
    -0.24
     dopo
    -0.24
     поÑģле
    -0.23
    After
    -0.22
    .after
    -0.22
     após
    -0.22
    POSITIVE LOGITS
    all
    0.42
     all
    0.39
    -all
    0.33
    éĥ½
    0.24
    .all
    0.24
    noon
    0.23
    =all
    0.21
    	all
    0.21
    thought
    0.21
     ÏĮλα
    0.21
    Activations Density 0.024%

    No Known Activations