© 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 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. 43458
    Prev
    Next
    INDEX
    Explanations

    statements regarding social justice issues and the ethical implications of state actions

    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
     him
    -0.23
    him
    -0.19
     lui
    -0.16
    velt
    -0.15
     ihn
    -0.15
    aney
    -0.15
    entials
    -0.15
    amins
    -0.14
    iÅŁi
    -0.14
    /tty
    -0.14
    POSITIVE LOGITS
     peoples
    0.59
     someone
    0.50
     somebody
    0.46
    someone
    0.43
     people
    0.39
     everyone
    0.39
    人çļĦ
    0.36
    Someone
    0.35
    人们
    0.35
     Someone
    0.35
    Activations Density 0.045%

    No Known Activations