© 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. 9188
    Prev
    Next
    INDEX
    Explanations

    phrases related to ease of use and accessibility

    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
    catid
    -0.16
    ware
    -0.14
     Reserve
    -0.14
    æµľ
    -0.14
    zo
    -0.14
    Exact
    -0.13
    iso
    -0.13
     Mechan
    -0.13
     revolution
    -0.13
    .reserve
    -0.13
    POSITIVE LOGITS
    åı¯
    0.43
     easily
    0.36
     ÙĤابÙĦ
    0.34
    atable
    0.33
     Easily
    0.33
    achable
    0.32
     åı¯
    0.32
    appable
    0.31
    oppable
    0.30
    vable
    0.30
    Activations Density 0.068%

    No Known Activations