© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 15200
    Prev
    Next
    INDEX
    Explanations

    references to ownership or possession related to objects

    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
    zon
    -0.17
    .bp
    -0.14
    minster
    -0.14
    ÑĨенÑĤ
    -0.14
     phenomenon
    -0.14
    -REAL
    -0.14
    ruh
    -0.14
    /welcome
    -0.14
    /proto
    -0.14
     phenomena
    -0.13
    POSITIVE LOGITS
     own
    0.31
     original
    0.27
     usual
    0.26
     accustomed
    0.25
     natural
    0.25
     normal
    0.24
     respective
    0.23
    own
    0.23
     assigned
    0.22
     appointed
    0.22
    Activations Density 0.165%

    No Known Activations