© 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. 8835
    Prev
    Next
    INDEX
    Explanations

    references to female representation and achievement in sports

    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
    oder
    -0.17
     likely
    -0.16
    åĵ¦
    -0.15
     uneven
    -0.14
     serve
    -0.14
    icom
    -0.14
    XP
    -0.14
    elian
    -0.14
    _advance
    -0.14
    ahlen
    -0.13
    POSITIVE LOGITS
     faith
    0.20
     support
    0.20
     SUPPORT
    0.20
     ä¿¡
    0.19
    /support
    0.19
    belief
    0.19
     belief
    0.19
    belie
    0.19
    ä¿¡
    0.19
     treatment
    0.19
    Activations Density 0.041%

    No Known Activations