© 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. 25442
    Prev
    Next
    INDEX
    Explanations

    sentences containing accusations or claims regarding actions and 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
    hood
    -0.20
    vf
    -0.17
     Hood
    -0.16
     hood
    -0.16
    æ´ŀ
    -0.15
    .EventHandler
    -0.15
    à¹Įà¹Ĥ
    -0.15
    .opensource
    -0.15
    hed
    -0.15
    hen
    -0.15
    POSITIVE LOGITS
    Har
    0.80
     Har
    0.78
     har
    0.77
     HAR
    0.71
    har
    0.70
    .har
    0.65
     harmon
    0.63
     Harvey
    0.63
     harvest
    0.63
     harmonic
    0.63
    Activations Density 0.008%

    No Known Activations