© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41987
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    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
    @yahoo
    -0.20
    @hotmail
    -0.17
    @gmail
    -0.15
    iegel
    -0.14
    pared
    -0.14
    enschaft
    -0.14
    ernals
    -0.13
    enders
    -0.13
    sel
    -0.13
    .useState
    -0.13
    POSITIVE LOGITS
    quer
    0.15
    HING
    0.15
    anky
    0.15
     ApplicationException
    0.15
    á»IJ
    0.14
     sta
    0.14
    WithError
    0.14
    ìĹĶ
    0.14
    inke
    0.13
    ovu
    0.13
    Activations Density 0.037%

    No Known Activations