© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33400
    Prev
    Next
    INDEX
    Explanations

    quoted speech and indicators of statements made by individuals

    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
    USA
    -0.15
    Äĥm
    -0.14
    GenerationStrategy
    -0.14
    aign
    -0.14
     USA
    -0.14
    Ã¼ÅŁ
    -0.14
    $MESS
    -0.14
    eza
    -0.14
    agne
    -0.14
    amt
    -0.14
    POSITIVE LOGITS
     there
    0.24
     whilst
    0.23
     while
    0.21
    there
    0.19
     There
    0.19
    while
    0.18
     mentre
    0.16
     unless
    0.16
    baugh
    0.15
     While
    0.15
    Activations Density 0.071%

    No Known Activations