© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8730
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to possession or ownership

    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
    EqualTo
    -0.15
     ADVISED
    -0.12
    --;
    -0.12
    [].
    -0.12
     Indeed
    -0.12
    typeorm
    -0.12
     implements
    -0.11
    æŀľ
    -0.11
     halde
    -0.11
    730
    -0.11
    POSITIVE LOGITS
     is
    0.29
    ï¼īãģ¯
    0.28
    "is
    0.25
    人ãģ¯
    0.24
     was
    0.23
    åŃIJãģ¯
    0.22
    çļĦæĺ¯
    0.21
     adalah
    0.21
     ê²ĥìĿĢ
    0.20
    ìŀ¥ìĿĢ
    0.20
    Activations Density 0.026%

    No Known Activations