© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal sentencing and justice outcomes

    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
    ulis
    -0.16
    à¹Ģà¸Ħล
    -0.15
    ucer
    -0.15
    ardy
    -0.15
     prosecuting
    -0.15
    adius
    -0.14
    æĢ¥
    -0.14
     sue
    -0.14
     Arrest
    -0.14
    ìĤ¬ë¬´
    -0.14
    POSITIVE LOGITS
     sentence
    0.43
     sentences
    0.41
     Sentence
    0.33
     Sent
    0.33
    sentence
    0.33
    Sentence
    0.30
    Sent
    0.29
    sent
    0.28
    .sent
    0.27
     SENT
    0.27
    Activations Density 0.070%

    No Known Activations