© 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. 22222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and support between individuals or organizations

    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
    eya
    -0.16
    UPI
    -0.15
    eyle
    -0.15
    ihn
    -0.15
    ега
    -0.14
    Ðĭ
    -0.14
    ecycle
    -0.13
     Leban
    -0.13
     Eg
    -0.13
     nackte
    -0.13
    POSITIVE LOGITS
     clients
    0.92
     client
    0.82
     Clients
    0.80
    clients
    0.71
     Client
    0.70
     customers
    0.68
    client
    0.67
    客æĪ·
    0.66
    Clients
    0.66
     clientes
    0.64
    Activations Density 0.039%

    No Known Activations