© 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. 14727
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and their affiliations

    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
    .ToolTip
    -0.12
    _asm
    -0.12
    Ñĸп
    -0.12
     же
    -0.11
     {{--<
    -0.11
    afil
    -0.11
     zoek
    -0.11
    .Adapter
    -0.11
    eyh
    -0.11
     åº
    -0.11
    POSITIVE LOGITS
     RuntimeObject
    0.14
    Ĩ
    0.13
    µ
    0.12
    BoundingClientRect
    0.12
    omitempty
    0.12
    Ł
    0.12
    chandle
    0.12
    Ī
    0.12
    jspx
    0.12
    @nate
    0.11
    Activations Density 1.324%

    No Known Activations