© 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. 24874
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial disclosures and conflicts of interest

    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
    ESSAGES
    -0.18
    adelphia
    -0.15
    å±±å¸Ĥ
    -0.15
    owski
    -0.15
    .TextAlignment
    -0.14
     circulating
    -0.13
    /sys
    -0.13
    olk
    -0.13
     tranh
    -0.13
    .Ordinal
    -0.12
    POSITIVE LOGITS
     disclosure
    0.36
     reporting
    0.33
     Disclosure
    0.32
    Disclosure
    0.31
     disclose
    0.30
     filing
    0.30
     disclosing
    0.30
     filed
    0.29
     disclosures
    0.28
     required
    0.28
    Activations Density 0.042%

    No Known Activations