© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 54159
    Prev
    Next
    INDEX
    Explanations

    references to crime, population statistics, and metrics related to social issues

    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
    alia
    -0.16
    ìĶ©
    -0.15
    çķ
    -0.15
    agas
    -0.14
    ênh
    -0.14
     sơ
    -0.13
    _compat
    -0.13
    ãģ®åŃIJ
    -0.13
     conjunto
    -0.13
    æı
    -0.13
    POSITIVE LOGITS
     due
    0.30
     since
    0.23
    due
    0.22
     over
    0.21
    Due
    0.20
     compared
    0.20
     caused
    0.20
     accompanies
    0.20
     following
    0.20
    since
    0.19
    Activations Density 0.105%

    No Known Activations