© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41876
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or place names

    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
    stav
    -0.14
    pline
    -0.14
     Khu
    -0.14
     #+#
    -0.13
    moz
    -0.13
    izia
    -0.13
    ì¶ľ
    -0.13
    erdem
    -0.13
    .Assembly
    -0.13
    erten
    -0.13
    POSITIVE LOGITS
     Wilkinson
    0.15
    aukee
    0.15
    waukee
    0.15
    aw
    0.14
    ocket
    0.14
    quoi
    0.14
    hoe
    0.14
    arie
    0.14
    oodle
    0.14
    ëį°ìĿ´íĬ¸
    0.13
    Activations Density 0.332%

    No Known Activations