© 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. 41686
    Prev
    Next
    INDEX
    Explanations

    statements about regulatory policies and their implications

    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
     Searching
    -0.17
    Searching
    -0.16
     suppress
    -0.15
     nors
    -0.15
    iego
    -0.15
     suppressed
    -0.14
     Ãĸn
    -0.14
     sparks
    -0.14
     crippling
    -0.14
     lur
    -0.14
    POSITIVE LOGITS
     causing
    0.35
     making
    0.30
     creating
    0.29
     having
    0.26
     giving
    0.25
     helping
    0.25
     putting
    0.25
     driving
    0.24
     bringing
    0.23
     taking
    0.23
    Activations Density 0.168%

    No Known Activations