© 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 EvalsExportsinterp-engineNEWAPI 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. 13134
    Prev
    Next
    INDEX
    Explanations

    references to legal offenses involving physical harm and animal welfare

    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
     Cham
    -0.16
    uations
    -0.16
    ุà¸Ĺ
    -0.15
     Lev
    -0.15
     Branch
    -0.14
    ä»°
    -0.14
    ĽĪ
    -0.14
     Kak
    -0.14
     toll
    -0.14
    _scheme
    -0.14
    POSITIVE LOGITS
    intree
    0.18
     inde
    0.18
     racially
    0.17
     GB
    0.16
    renc
    0.16
    wil
    0.16
    GB
    0.15
    gba
    0.15
    abet
    0.15
    ycz
    0.15
    Activations Density 0.048%

    No Known Activations