© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    phrases or numbers associated with family dynamics and group sizes

    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
    äºĮ人
    -0.21
    .flink
    -0.17
    -valu
    -0.17
    两人
    -0.17
    iag
    -0.16
     Utf
    -0.16
    SSIP
    -0.15
    .mj
    -0.15
    ège
    -0.14
    кÑĥл
    -0.14
    POSITIVE LOGITS
     sons
    0.34
     daughters
    0.31
     children
    0.30
    sons
    0.26
     Sons
    0.23
     Children
    0.23
     kids
    0.22
     nie
    0.21
     grown
    0.21
    children
    0.21
    Activations Density 0.043%

    No Known Activations