© 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. 29162
    Prev
    Next
    INDEX
    Explanations

    instances of the word "listed," indicating a focus on enumerating or documenting items or individuals

    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
    chest
    -0.16
    List
    -0.15
    zan
    -0.15
    zu
    -0.15
    /from
    -0.14
    umni
    -0.14
    /rss
    -0.14
    steen
    -0.14
    ives
    -0.14
    suit
    -0.14
    POSITIVE LOGITS
    ened
    0.25
    eners
    0.24
    agem
    0.23
    ings
    0.22
    owel
    0.21
    ening
    0.20
    -unstyled
    0.19
    ner
    0.19
    icle
    0.19
    erv
    0.18
    Activations Density 0.018%

    No Known Activations