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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41303
    Prev
    Next
    INDEX
    Explanations

    technical terms related to equipment operation and control

    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
    aeda
    -0.13
    Ñıл
    -0.13
     Mou
    -0.13
    ån
    -0.13
     koc
    -0.13
    bersome
    -0.13
    éĢł
    -0.13
     Trap
    -0.13
    trap
    -0.13
    NAV
    -0.13
    POSITIVE LOGITS
     adjust
    0.57
     Adjust
    0.56
     adjustment
    0.56
     adjusting
    0.53
     adjustments
    0.52
    Adjust
    0.52
     Adjustment
    0.51
    -adjust
    0.51
    adjust
    0.50
     adjusts
    0.48
    Activations Density 0.038%

    No Known Activations