© 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. 43578
    Prev
    Next
    INDEX
    Explanations

    words related to relationships or connections among entities

    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
     Decom
    -0.18
    ãĥ³ãĤ¬
    -0.18
    .DialogResult
    -0.16
    agua
    -0.16
     Diss
    -0.15
     Dev
    -0.15
    Deque
    -0.15
     Dial
    -0.15
     Dwight
    -0.15
     Dias
    -0.15
    POSITIVE LOGITS
     drop
    1.27
     Drop
    1.16
     drops
    1.10
    drop
    1.09
    Drop
    1.08
    -drop
    1.08
     dropped
    1.07
     dropping
    1.06
     Dro
    1.02
     DROP
    1.01
    Activations Density 0.008%

    No Known Activations