© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    dramatic or pivotal moments in a narrative

    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
    åģľ
    -0.14
    INUX
    -0.14
    .page
    -0.14
    &page
    -0.14
    åĭŁ
    -0.14
    IRS
    -0.14
    osen
    -0.14
     Depths
    -0.14
    parm
    -0.14
     priv
    -0.13
    POSITIVE LOGITS
     gro
    0.24
     Stretch
    0.24
     stretch
    0.23
     stretching
    0.22
     rubbing
    0.22
     stretches
    0.22
     stretched
    0.21
    Stretch
    0.21
     rub
    0.21
    stretch
    0.20
    Activations Density 0.015%

    No Known Activations