© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and mathematical expressions

    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
    ÑĢÑıд
    -0.20
     kav
    -0.17
     serge
    -0.16
    493
    -0.14
    IRROR
    -0.14
    944
    -0.14
    ading
    -0.14
    RuleContext
    -0.14
    stan
    -0.14
     thụ
    -0.14
    POSITIVE LOGITS
    250
    0.39
    750
    0.38
    150
    0.35
    500
    0.33
    950
    0.31
    450
    0.30
    125
    0.29
    350
    0.29
    850
    0.28
    550
    0.28
    Activations Density 0.034%

    No Known Activations