© 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. 30021
    Prev
    Next
    INDEX
    Explanations

    references to political events and transitions involving leadership changes

    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
    adt
    -0.16
    TouchUpInside
    -0.15
    erva
    -0.15
    fur
    -0.14
    odel
    -0.14
     Hoy
    -0.14
    ãĥ«ãĥī
    -0.14
    ategorized
    -0.14
    ¥IJ
    -0.13
     pÅĻest
    -0.13
    POSITIVE LOGITS
     ou
    0.47
     topp
    0.37
     overthrow
    0.36
     deposition
    0.35
     removal
    0.34
     top
    0.31
     remove
    0.31
     Removal
    0.30
     dep
    0.29
     depos
    0.29
    Activations Density 0.055%

    No Known Activations