© 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. 63745
    Prev
    Next
    INDEX
    Explanations

    statements regarding the effects and dangers of synthetic substances

    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
    μά
    -0.17
    lector
    -0.16
    arent
    -0.15
    amel
    -0.15
    à¹Ħà¸Ĥ
    -0.15
    enty
    -0.14
     suffers
    -0.14
     intrusive
    -0.13
    lag
    -0.13
    κÏĦη
    -0.13
    POSITIVE LOGITS
     kill
    0.31
     cause
    0.28
     destroy
    0.27
     Cause
    0.26
     Kill
    0.26
     kills
    0.25
     killed
    0.24
    Kill
    0.24
    Cause
    0.23
    kill
    0.23
    Activations Density 0.143%

    No Known Activations