© 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. 41252
    Prev
    Next
    INDEX
    Explanations

    references to comic book characters and their interactions

    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
     insp
    -0.15
    rens
    -0.14
    hetto
    -0.14
    ahat
    -0.14
    zilla
    -0.14
    ÑĨеÑģ
    -0.14
     halo
    -0.14
    ramer
    -0.14
    iba
    -0.14
    .getStyle
    -0.14
    POSITIVE LOGITS
     Marvel
    0.25
    616
    0.25
    Marvel
    0.21
     AIM
    0.21
     Pun
    0.21
     knull
    0.20
     Deadpool
    0.20
     Avengers
    0.19
     Coul
    0.19
     HY
    0.18
    Activations Density 0.051%

    No Known Activations