© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    sentences related to crime statistics and trends

    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
     Kok
    -0.17
    aterno
    -0.16
    ÅĻet
    -0.16
    ìĤ
    -0.14
    ä¸Ńæĸĩ
    -0.14
    ÑĢава
    -0.14
    еÑģп
    -0.14
    rex
    -0.14
    ovat
    -0.14
    uien
    -0.13
    POSITIVE LOGITS
     crime
    0.63
     Crime
    0.51
    crime
    0.49
     crimes
    0.45
    Crime
    0.44
    -cr
    0.36
    çĬ¯ç½ª
    0.34
     Crimes
    0.34
     criminal
    0.31
    .cr
    0.29
    Activations Density 0.099%

    No Known Activations