© 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. 24004
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Maria."

    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
    ven
    -0.15
    etary
    -0.15
    veau
    -0.15
    lass
    -0.15
    stad
    -0.14
     må
    -0.14
     Rena
    -0.14
    ãĥĬãĥ¼
    -0.14
    ken
    -0.14
    pend
    -0.14
    POSITIVE LOGITS
     Elena
    0.16
    earing
    0.16
    erce
    0.15
    -sama
    0.15
     Gore
    0.15
     Carolina
    0.15
    ingleton
    0.15
    zell
    0.14
    estre
    0.14
    ially
    0.14
    Activations Density 0.009%

    No Known Activations