© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 43587
    Prev
    Next
    INDEX
    Explanations

    references to violence and criminal activities

    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
    üçük
    -0.15
    540
    -0.15
    ucle
    -0.15
    ¸
    -0.15
    ieu
    -0.14
    Conv
    -0.14
     footnote
    -0.14
     conv
    -0.14
    udas
    -0.14
     ↵
    -0.14
    POSITIVE LOGITS
     gun
    0.35
     knife
    0.27
    gun
    0.26
    -gun
    0.26
     kn
    0.25
     Gun
    0.23
    knife
    0.22
    æŀª
    0.22
     Knife
    0.21
     guns
    0.21
    Activations Density 0.020%

    No Known Activations