© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9206
    Prev
    Next
    INDEX
    Explanations

    references to legal settings and court proceedings

    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
    æĸ¹
    -0.15
    ť
    -0.14
    .jquery
    -0.14
    _ALIGNMENT
    -0.14
    elu
    -0.13
    ALCHEMY
    -0.13
    /background
    -0.13
    Protected
    -0.13
     themselves
    -0.13
    aille
    -0.13
    POSITIVE LOGITS
     judge
    0.17
    ouch
    0.16
    à¸Ľà¸£à¸°à¸Īำ
    0.16
    rooms
    0.15
    judge
    0.15
    uez
    0.15
    idlo
    0.15
    -thumbnails
    0.15
     for
    0.14
    तर
    0.14
    Activations Density 0.010%

    No Known Activations