© 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. 28699
    Prev
    Next
    INDEX
    Explanations

    expressions of belief, knowledge, and decision-making

    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
     that
    -0.41
    that
    -0.34
     hogy
    -0.33
     ÑĩÑĤо
    -0.29
     daÃŁ
    -0.29
    	that
    -0.28
     rằng
    -0.27
     dass
    -0.27
     että
    -0.27
     bahwa
    -0.26
    POSITIVE LOGITS
     they
    0.34
     he
    0.26
     we
    0.23
    they
    0.23
     there
    0.23
     she
    0.22
     it
    0.22
     THEY
    0.21
     They
    0.19
     они
    0.18
    Activations Density 0.032%

    No Known Activations