© 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. 41786
    Prev
    Next
    INDEX
    Explanations

    Key concepts associated with memories and impactful emotional experiences

    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
     rounded
    -0.15
     completes
    -0.15
     completed
    -0.15
     blind
    -0.15
     complet
    -0.14
     Comple
    -0.14
     touching
    -0.14
    emit
    -0.14
     Stra
    -0.14
    icana
    -0.14
    POSITIVE LOGITS
     stick
    0.28
     et
    0.28
     stuck
    0.27
     forever
    0.26
     Stick
    0.25
     permanently
    0.25
     sticks
    0.25
    Stick
    0.25
     burned
    0.24
     burnt
    0.24
    Activations Density 0.042%

    No Known Activations