© 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. 15651
    Prev
    Next
    INDEX
    Explanations

    instances of police conduct and interactions with the public

    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
    .Active
    -0.16
    idd
    -0.14
    antu
    -0.14
    insk
    -0.14
    etros
    -0.14
    pollo
    -0.14
    @class
    -0.14
    917
    -0.14
    sek
    -0.14
    otor
    -0.14
    POSITIVE LOGITS
     dealing
    0.62
     dealings
    0.56
     deal
    0.53
     interact
    0.53
     interactions
    0.53
     interaction
    0.49
     interacting
    0.49
     deals
    0.48
     dealt
    0.48
    deal
    0.48
    Activations Density 0.015%

    No Known Activations