© 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. 41717
    Prev
    Next
    INDEX
    Explanations

    references to characters or personas in media

    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
    auer
    -0.15
    èĽĽ
    -0.15
    Ã¤ÃŁ
    -0.15
     Rebel
    -0.15
    _DS
    -0.14
    forman
    -0.14
    ilon
    -0.14
     è©ķ
    -0.14
    omite
    -0.14
    éĺħ读次æķ°
    -0.14
    POSITIVE LOGITS
     Hats
    0.17
     Hits
    0.16
     Sous
    0.16
     ì¸
    0.15
     Takes
    0.15
     Subaru
    0.15
    Sou
    0.15
     Haj
    0.15
     Nag
    0.14
     gen
    0.14
    Activations Density 0.050%

    No Known Activations