© 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. 54492
    Prev
    Next
    INDEX
    Explanations

    mentions of community engagement and collaboration initiatives

    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
     nackte
    -0.15
     ########.
    -0.14
    abella
    -0.13
    ç¦
    -0.13
     {{--<
    -0.13
    .getOwnProperty
    -0.13
    ore
    -0.13
    ach
    -0.13
     reuseIdentifier
    -0.12
    igs
    -0.12
    POSITIVE LOGITS
    reesome
    0.15
    úi
    0.14
    panion
    0.14
    bÃŃr
    0.14
    idla
    0.13
    anst
    0.13
    (æľ¨
    0.13
    .swt
    0.13
    ucha
    0.13
    TEGER
    0.13
    Activations Density 0.033%

    No Known Activations