© 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. 63245
    Prev
    Next
    INDEX
    Explanations

    references to investigations and legal terms related to formal inquiries

    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
     Eaton
    -0.13
    eus
    -0.12
    ear
    -0.12
     Lam
    -0.12
    .dot
    -0.12
    ÑijÑĤ
    -0.11
    .scalablytyped
    -0.11
    elda
    -0.11
    éra
    -0.11
    udu
    -0.11
    POSITIVE LOGITS
     em
    0.82
     EM
    0.79
    EM
    0.74
     Emp
    0.74
    em
    0.73
    -em
    0.72
    Emp
    0.70
    emp
    0.66
    .em
    0.65
    Em
    0.64
    Activations Density 0.008%

    No Known Activations