© 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. 55365
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright and fair use of creative works

    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
    aea
    -0.16
    гал
    -0.14
     archive
    -0.14
    esta
    -0.14
    ium
    -0.14
     exit
    -0.14
    benh
    -0.13
    bx
    -0.13
     UN
    -0.13
    à¸Ńà¸Ń
    -0.13
    POSITIVE LOGITS
     works
    0.41
     Works
    0.35
    works
    0.33
    Works
    0.30
     obras
    0.24
    ä½ľåĵģ
    0.22
     ÎŃÏģγ
    0.21
    Protected
    0.21
     protect
    0.20
     obra
    0.20
    Activations Density 0.033%

    No Known Activations