© 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. 33364
    Prev
    Next
    INDEX
    Explanations

    relationships between natural rewards, addiction, and the brain's reward system

    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
    semb
    -0.16
    letal
    -0.14
    esy
    -0.14
    ÅĻes
    -0.14
    ENCIL
    -0.13
    ancellation
    -0.13
     Bene
    -0.13
     vitam
    -0.13
     Abort
    -0.13
    swick
    -0.13
    POSITIVE LOGITS
     reward
    0.40
     rewards
    0.32
     Reward
    0.32
    reward
    0.29
    Reward
    0.28
     rewarding
    0.28
     pleasure
    0.27
     Rewards
    0.27
     ple
    0.26
    _reward
    0.24
    Activations Density 0.036%

    No Known Activations