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

    Neuronpedia

    Jacobian LensNEW
    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. 14898
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate personal statements or reports from the author

    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
    umn
    -0.15
     diyor
    -0.13
    eras
    -0.13
    ired
    -0.13
    Ñģок
    -0.13
    ÌĪ
    -0.13
    pany
    -0.13
    agna
    -0.13
    ħ
    -0.13
     legitim
    -0.12
    POSITIVE LOGITS
     previously
    0.38
     already
    0.33
     covered
    0.29
     mentioned
    0.27
    Previously
    0.27
    already
    0.25
     earlier
    0.25
     pointed
    0.25
     discussed
    0.25
     Previously
    0.25
    Activations Density 0.070%

    No Known Activations