© 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. 42455
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or policy adjustments in social contexts

    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
    ood
    -0.15
     Souls
    -0.14
    kem
    -0.14
     dù
    -0.14
     xuyên
    -0.13
    rowse
    -0.13
    quier
    -0.13
    fal
    -0.13
    andy
    -0.13
    lal
    -0.13
    POSITIVE LOGITS
     to
    0.46
     accordingly
    0.34
     so
    0.33
     ÑĩÑĤобÑĭ
    0.30
     Äijá»ĥ
    0.28
     Ñīоб
    0.23
     into
    0.23
     inorder
    0.23
    ToFit
    0.22
    sto
    0.22
    Activations Density 0.111%

    No Known Activations