© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41075
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "just" along with related actions and statuses

    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
     already
    -0.28
     eventually
    -0.25
     eventual
    -0.24
     later
    -0.23
     Already
    -0.22
    already
    -0.20
    Already
    -0.19
     ultimately
    -0.17
     subsequent
    -0.17
    event
    -0.17
    POSITIVE LOGITS
    åĪļ
    0.23
     finishing
    0.22
     finish
    0.21
     finished
    0.20
     xong
    0.20
     finishes
    0.20
     Finished
    0.18
     completing
    0.18
    ãģ°ãģĭãĤĬ
    0.17
    Completion
    0.17
    Activations Density 0.025%

    No Known Activations