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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 44530
    Prev
    Next
    INDEX
    Explanations

    references to migration and its associated dangers

    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
     вÑĸдвÑĸд
    -0.16
     Ramp
    -0.15
    oren
    -0.15
    inne
    -0.14
    opp
    -0.14
    Dlg
    -0.14
    ourd
    -0.14
    _probe
    -0.14
    há
    -0.14
    تباط
    -0.14
    POSITIVE LOGITS
     migration
    0.28
     migrants
    0.27
     Migration
    0.27
     migr
    0.25
     crossing
    0.25
     migrant
    0.24
     crossings
    0.23
     border
    0.23
     Border
    0.23
     irregular
    0.23
    Activations Density 0.111%

    No Known Activations