Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 72
    Prev
    Next
    INDEX
    Explanations

    numerical data presented in a specific format

    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
    1
    -0.21
    2
    -0.20
    3
    -0.20
    4
    -0.19
    5
    -0.17
    10
    -0.17
    chemas
    -0.17
    orian
    -0.17
    ëį°ìĿ´íĬ¸
    -0.16
    12
    -0.15
    POSITIVE LOGITS
    ï¸ı
    0.45
    â̳
    0.23
    s
    0.23
    â̲
    0.21
    six
    0.20
    ½
    0.20
    etheless
    0.19
    e
    0.17
    nbsp
    0.17
    adays
    0.16
    Activations Density 0.002%

    No Known Activations