© 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. 54255
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing changes and adaptations over time

    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
    imits
    -0.17
    utex
    -0.13
    ampie
    -0.13
    omik
    -0.13
     prolonged
    -0.13
    oder
    -0.13
    827
    -0.12
    dorf
    -0.12
    OVE
    -0.12
    AKER
    -0.12
    POSITIVE LOGITS
     changing
    0.59
    changing
    0.51
    -changing
    0.50
     Changing
    0.50
     dynamic
    0.49
    Changing
    0.47
     constantly
    0.45
     change
    0.44
     Dynamic
    0.43
    dynamic
    0.42
    Activations Density 0.039%

    No Known Activations