© 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. 28701
    Prev
    Next
    INDEX
    Explanations

    references to violence against unarmed individuals

    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
    acter
    -0.15
    анÑģи
    -0.15
     kå
    -0.14
    Ìĥ
    -0.14
    py
    -0.13
     underlying
    -0.13
    ENTA
    -0.13
    .Shared
    -0.13
    ãĥĥãĥĹ
    -0.13
    _NATIVE
    -0.13
    POSITIVE LOGITS
     innocent
    0.51
     innoc
    0.40
     Innoc
    0.40
     innocence
    0.32
     vulnerable
    0.29
     harmless
    0.28
     unarmed
    0.27
     civilians
    0.27
     inoc
    0.27
     peaceful
    0.26
    Activations Density 0.092%

    No Known Activations