Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63101
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their roles

    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
     Senior
    -0.17
    stateParams
    -0.15
    alo
    -0.14
     State
    -0.14
    æ´ĭ
    -0.14
     WARN
    -0.14
    upos
    -0.14
     Central
    -0.14
    Votre
    -0.14
    achinery
    -0.14
    POSITIVE LOGITS
    ardu
    0.16
    ades
    0.15
     acting
    0.15
    å°Ķ
    0.15
     Vive
    0.15
     Acting
    0.15
    .Doc
    0.14
    é§
    0.14
    ENCY
    0.14
    .scalablytyped
    0.14
    Activations Density 0.024%

    No Known Activations