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. 54525
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person, particularly their name

    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
    tty
    -0.18
    óż
    -0.15
    asa
    -0.15
    NamedQuery
    -0.15
    paration
    -0.14
    ashion
    -0.14
    ometown
    -0.14
    lsen
    -0.14
    è¶³
    -0.14
    ruz
    -0.14
    POSITIVE LOGITS
    patrick
    0.38
    gerald
    0.37
    erald
    0.26
    sim
    0.23
    roy
    0.19
    Patrick
    0.19
    ERAL
    0.18
     Fitzgerald
    0.18
    ibbon
    0.18
     Gerald
    0.18
    Activations Density 0.003%

    No Known Activations