Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63102
    Prev
    Next
    INDEX
    Explanations

    concepts related to tissue regeneration and engineering

    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
    igne
    -0.14
    562
    -0.14
    prend
    -0.14
     schl
    -0.14
    opis
    -0.14
    295
    -0.14
    unts
    -0.14
    Į¨
    -0.14
    .SelectedValue
    -0.13
    rear
    -0.13
    POSITIVE LOGITS
     tissue
    0.38
     tissues
    0.35
     connect
    0.34
     Connect
    0.28
    connect
    0.26
     basement
    0.24
     tun
    0.24
    Connect
    0.23
     cart
    0.23
    -connect
    0.23
    Activations Density 0.040%

    No Known Activations