© 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. 22044
    Prev
    Next
    INDEX
    Explanations

    derogatory or inflammatory remarks made about individuals or groups, particularly in a political context

    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
    atio
    -0.15
    ATIO
    -0.14
     Bard
    -0.13
     eject
    -0.13
    :///
    -0.13
     Hart
    -0.13
    ös
    -0.13
    PackageManager
    -0.13
     while
    -0.12
     Sho
    -0.12
    POSITIVE LOGITS
    roud
    0.16
    velte
    0.14
    sÃŃ
    0.14
     misunder
    0.13
     Resets
    0.13
    iev
    0.13
    ì¦Ī
    0.13
     Cleans
    0.12
     ---------------------------------------------------------------------------↵
    0.12
    ÑĤал
    0.12
    Activations Density 1.507%

    No Known Activations