© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 42032
    Prev
    Next
    INDEX
    Explanations

    references to personal information and financial details

    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
    SSIP
    -0.14
    Ø
    -0.14
    -pocket
    -0.13
    ůst
    -0.13
    anka
    -0.13
    .paging
    -0.13
    cape
    -0.13
    orent
    -0.13
    ingo
    -0.12
    ige
    -0.12
    POSITIVE LOGITS
     information
    0.68
     details
    0.53
    ä¿¡æģ¯
    0.53
    information
    0.53
     info
    0.51
     Information
    0.47
    Information
    0.43
     informations
    0.42
     INFORMATION
    0.42
    æĥħåł±
    0.42
    Activations Density 0.065%

    No Known Activations