© 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. 15150
    Prev
    Next
    INDEX
    Explanations

    phrases that signify significant changes or control in circumstances, particularly in political or military contexts

    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
     mess
    -0.15
    /uploads
    -0.15
     ìĹ°
    -0.14
    anio
    -0.14
    .inputs
    -0.14
    deg
    -0.13
     Greenwood
    -0.13
    _FILENAME
    -0.13
    erk
    -0.13
    ãĥĶãĥ¼
    -0.13
    POSITIVE LOGITS
     balance
    0.40
     outcome
    0.36
     Balance
    0.34
    balance
    0.33
     balances
    0.31
    outcome
    0.30
     momentum
    0.30
    Balance
    0.29
     Outcome
    0.29
    Outcome
    0.27
    Activations Density 0.040%

    No Known Activations