© 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. 30531
    Prev
    Next
    INDEX
    Explanations

    references to abuse and corruption in institutional contexts

    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
    echan
    -0.15
    à¸Ńà¸Ń
    -0.15
    hek
    -0.14
     culpa
    -0.14
    WebResponse
    -0.14
    swer
    -0.14
    åĪº
    -0.14
     suic
    -0.14
    448
    -0.14
     Intercept
    -0.13
    POSITIVE LOGITS
     abuse
    0.67
     Abuse
    0.57
     mist
    0.57
     abuses
    0.47
     abused
    0.47
     abusive
    0.43
     abusing
    0.43
     malt
    0.43
     Mist
    0.36
    mist
    0.34
    Activations Density 0.069%

    No Known Activations