© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 45180
    Prev
    Next
    INDEX
    Explanations

    terms related to military aid and support in conflict situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Interaction
    -0.15
     Putin
    -0.14
    ارج
    -0.14
    gra
    -0.14
    DMA
    -0.14
    /Grid
    -0.14
     Spoj
    -0.14
    /Peak
    -0.14
    usa
    -0.14
    بش
    -0.14
    POSITIVE LOGITS
     rebels
    0.20
     proxies
    0.19
     groups
    0.18
     moderate
    0.18
     overthrow
    0.18
     factions
    0.17
     antic
    0.16
     Moderate
    0.16
     clients
    0.16
     forces
    0.16
    Activations Density 0.036%

    No Known Activations