© 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. 15486
    Prev
    Next
    INDEX
    Explanations

    the phrase "of" in various contexts, suggesting a focus on possessive or relational structures within the text

    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
    ä¸ĢåĪĩ
    -0.17
     Äijây
    -0.16
    çļĦè¯Ŀ
    -0.15
    人æ°Ĺ
    -0.15
    à¸Ħ
    -0.15
    erez
    -0.14
     célib
    -0.14
    abouts
    -0.14
    umber
    -0.14
    å
    -0.14
    POSITIVE LOGITS
     being
    0.31
     having
    0.29
       
    0.27
    course
    0.27
     sorts
    0.27
    being
    0.24
    -course
    0.20
     course
    0.20
    having
    0.20
     Being
    0.20
    Activations Density 0.528%

    No Known Activations