© 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. 12866
    Prev
    Next
    INDEX
    Explanations

    terms related to scandal or controversial behavior

    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
    elts
    -0.17
    _inches
    -0.16
    alon
    -0.16
    ÑĢок
    -0.15
    manship
    -0.15
    uforia
    -0.15
    ingles
    -0.15
    eled
    -0.14
    plr
    -0.14
    /ion
    -0.14
    POSITIVE LOGITS
    ous
    1.03
    ously
    0.81
    OUS
    0.62
    uous
    0.44
    oust
    0.43
    ouser
    0.40
    ious
    0.37
    ouse
    0.36
    rous
    0.35
    ized
    0.31
    Activations Density 0.026%

    No Known Activations