© 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. 30194
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration policies and integration issues

    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
    rani
    -0.14
    nak
    -0.14
    /Instruction
    -0.13
    /XMLSchema
    -0.13
    deÅŁ
    -0.13
    :Event
    -0.13
    rowsable
    -0.13
    /alert
    -0.13
     jadx
    -0.13
    ãģĹãĤĥ
    -0.12
    POSITIVE LOGITS
     vet
    0.60
     screening
    0.56
    -screen
    0.48
    screen
    0.47
     Screening
    0.47
     screenings
    0.45
     screen
    0.44
     screened
    0.42
    Screen
    0.41
     screens
    0.41
    Activations Density 0.043%

    No Known Activations