© 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 EvalsExportsinterp-engineNEWAPI 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. 12617
    Prev
    Next
    INDEX
    Explanations

    references to young people and their challenges

    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
    ardy
    -0.16
    irit
    -0.14
    rouch
    -0.14
    oothing
    -0.14
    udden
    -0.14
    ripper
    -0.14
    Äħż
    -0.14
    ingham
    -0.14
    iese
    -0.14
    adam
    -0.14
    POSITIVE LOGITS
     aged
    0.22
     freshly
    0.19
     fresh
    0.18
    aged
    0.17
    -aged
    0.17
     today
    0.17
     entering
    0.17
    agers
    0.16
     especially
    0.16
     growing
    0.15
    Activations Density 0.041%

    No Known Activations