© 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. 15698
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and economic comparisons

    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
     ComVisible
    -0.15
    агаÑĤо
    -0.15
    ãĥ¼ãĥĩ
    -0.14
     moden
    -0.14
    ãĥ©ãĥ³ãĥī
    -0.14
    aub
    -0.14
    VT
    -0.14
    /Peak
    -0.14
    /Instruction
    -0.14
    ATAB
    -0.14
    POSITIVE LOGITS
     East
    0.62
     east
    0.57
    East
    0.52
     West
    0.51
     coast
    0.49
     west
    0.49
     Coast
    0.42
    West
    0.42
     EAST
    0.42
    east
    0.40
    Activations Density 0.050%

    No Known Activations