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

    Neuronpedia

    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. 41903
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and parameters related to polynomial functions

    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
    ippet
    -0.14
    /lists
    -0.14
    upa
    -0.14
     ade
    -0.13
    ãĥ¼ãĥ«ãĥī
    -0.13
    ohl
    -0.13
    cosa
    -0.13
    imestone
    -0.13
    ÙĪÙĬر
    -0.13
    loo
    -0.13
    POSITIVE LOGITS
     Q
    0.56
    Q
    0.48
     q
    0.47
    _q
    0.43
    q
    0.40
    	Q
    0.38
    _Q
    0.36
    .q
    0.36
    .Q
    0.35
    -Q
    0.35
    Activations Density 0.033%

    No Known Activations