© 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. 54017
    Prev
    Next
    INDEX
    Explanations

    terms related to restrictions or prohibitions

    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
    onth
    -0.15
    eil
    -0.14
    ırak
    -0.13
    ylland
    -0.13
    builtin
    -0.13
    éļİ
    -0.13
    ãĥªãĥ¼ãĤº
    -0.13
    kle
    -0.12
    λεÏį
    -0.12
    kil
    -0.12
    POSITIVE LOGITS
     from
    0.31
    from
    0.23
     entry
    0.22
    ishment
    0.22
     FROM
    0.20
     by
    0.20
     forever
    0.20
     altogether
    0.20
    ãģĭãĤī
    0.18
    dden
    0.18
    Activations Density 0.048%

    No Known Activations