© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    connections and experiences related to success and opportunity in the context of education and funding

    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
    processable
    -0.17
    ihn
    -0.16
    å¡ļ
    -0.14
    kea
    -0.14
    dictions
    -0.13
    uckle
    -0.13
    alous
    -0.13
    parity
    -0.13
    nock
    -0.13
    grammar
    -0.13
    POSITIVE LOGITS
     connections
    0.57
     contacts
    0.55
     networks
    0.44
     network
    0.44
     Contacts
    0.43
     Connections
    0.43
    contacts
    0.43
    connections
    0.42
     connection
    0.39
    Connections
    0.37
    Activations Density 0.049%

    No Known Activations