© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    actions associated with male behavior and training

    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
    allon
    -0.18
     conspiracy
    -0.14
     Nose
    -0.14
    bler
    -0.14
     Xxx
    -0.14
    etri
    -0.14
    ateria
    -0.13
    oty
    -0.13
    ät
    -0.13
     Conspiracy
    -0.13
    POSITIVE LOGITS
     kill
    0.55
     killing
    0.55
     kills
    0.51
     killed
    0.46
    kill
    0.45
     Kill
    0.45
     killings
    0.43
    Kill
    0.43
     Killing
    0.42
    殺
    0.41
    Activations Density 0.075%

    No Known Activations