© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14256
    Prev
    Next
    INDEX
    Explanations

    expressions related to respect and demands in the context of social issues and rights

    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
    же
    -0.15
    amed
    -0.14
    crement
    -0.14
    è£ķ
    -0.14
    /rc
    -0.14
    ike
    -0.14
    nave
    -0.14
    yun
    -0.14
    ç´Ķ
    -0.14
    ideos
    -0.14
    POSITIVE LOGITS
     authority
    0.24
     Eld
    0.22
     boundaries
    0.21
     differences
    0.21
     opinion
    0.21
     privacy
    0.21
     opinions
    0.20
     elders
    0.20
     wishes
    0.20
     traditions
    0.19
    Activations Density 0.022%

    No Known Activations