© 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. 12923
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names

    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
    (es
    -0.17
    ful
    -0.16
    (s
    -0.15
    orem
    -0.14
    ứng
    -0.14
    curity
    -0.14
    eid
    -0.14
     Byl
    -0.13
    .btnClose
    -0.13
    ombok
    -0.13
    POSITIVE LOGITS
    .au
    0.46
    .ua
    0.28
    .br
    0.27
    .mx
    0.25
    lify
    0.22
    .bd
    0.19
    .cn
    0.19
    .cy
    0.19
    sense
    0.19
    .pk
    0.19
    Activations Density 0.054%

    No Known Activations