© 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. 43228
    Prev
    Next
    INDEX
    Explanations

    words related to necessary actions or requirements

    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
    иваÑİÑĤ
    -0.17
    лÑıли
    -0.16
    ennes
    -0.16
    ëłĢ
    -0.15
    лÑıÑİÑĤ
    -0.15
    иваеÑĤ
    -0.15
    oblin
    -0.15
    лÑıÑİÑĤÑĮ
    -0.15
    лÑıÑĶ
    -0.15
    ÑĢÑĥеÑĤ
    -0.14
    POSITIVE LOGITS
     itself
    0.61
     siÄĻ
    0.57
     themselves
    0.56
     zich
    0.56
     sich
    0.56
     herself
    0.52
     himself
    0.49
     Himself
    0.42
     se
    0.41
    ÑģÑı
    0.41
    Activations Density 0.008%

    No Known Activations