© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and police procedures

    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
    ĵĺ
    -0.14
    uels
    -0.14
    igit
    -0.14
     Manila
    -0.14
     nev
    -0.14
    ogo
    -0.14
     Rip
    -0.14
    illac
    -0.14
     Bing
    -0.13
    chor
    -0.13
    POSITIVE LOGITS
     Brow
    0.44
     Lauderdale
    0.36
    954
    0.34
     Miami
    0.33
    Miami
    0.32
     Palm
    0.31
     Coconut
    0.30
     Coral
    0.28
     Pom
    0.26
     brow
    0.26
    Activations Density 0.033%

    No Known Activations