Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 12
    Prev
    Next
    INDEX
    Explanations

    references to chemical weapons and their alleged usage in conflict

    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
    aukee
    -0.15
    qv
    -0.14
     Latter
    -0.14
    bohydr
    -0.14
    mith
    -0.14
    chaft
    -0.13
    ju
    -0.13
    tement
    -0.13
    ASIC
    -0.13
    ascript
    -0.13
    POSITIVE LOGITS
     chemical
    0.38
     Chemical
    0.32
    Chem
    0.31
    chemical
    0.30
     chem
    0.27
     Chem
    0.25
     chemicals
    0.25
     chlorine
    0.24
     sar
    0.23
    åĮĸåѦ
    0.23
    Activations Density 0.080%

    No Known Activations