© 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. 54783
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific male individual

    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
    omial
    -0.17
    weep
    -0.16
    peare
    -0.15
    ng
    -0.15
    onne
    -0.15
    ãģ£ãģ¨
    -0.15
    lia
    -0.14
    mag
    -0.14
    ë¶Ħ
    -0.14
    flu
    -0.14
    POSITIVE LOGITS
    idelberg
    0.23
    brew
    0.22
    athy
    0.21
    ikki
    0.20
    addresses
    0.19
    ights
    0.19
    inz
    0.19
    ated
    0.19
    ald
    0.18
    fce
    0.18
    Activations Density 0.024%

    No Known Activations