© 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. 15271
    Prev
    Next
    INDEX
    Explanations

    the letter 'N' followed by numbers or specific names

    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
    ode
    -0.18
    ames
    -0.17
    owa
    -0.17
    ав
    -0.17
    аÑģ
    -0.17
    Å¡ka
    -0.16
    avo
    -0.16
    av
    -0.16
    SPA
    -0.16
    AME
    -0.16
    POSITIVE LOGITS
    unner
    0.18
    gon
    0.18
    atives
    0.17
     orth
    0.17
    RIC
    0.16
    anking
    0.16
     gon
    0.16
    olson
    0.16
    ong
    0.16
    atch
    0.15
    Activations Density 0.031%

    No Known Activations