© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63619
    Prev
    Next
    INDEX
    Explanations

    locations and events related to the band's tours and concerts

    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
    emale
    -0.15
    æĵļ
    -0.15
     Stanton
    -0.15
    iya
    -0.14
    hoc
    -0.14
    skirts
    -0.14
    @d
    -0.14
     actionable
    -0.14
    νε
    -0.14
    çĴ°
    -0.14
    POSITIVE LOGITS
     Fill
    0.21
     Shea
    0.19
     fill
    0.17
    Fill
    0.17
    MSG
    0.16
    IRST
    0.16
    exion
    0.16
     Gross
    0.16
    å¡«
    0.14
     bic
    0.14
    Activations Density 0.019%

    No Known Activations