© 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. 63662
    Prev
    Next
    INDEX
    Explanations

    terms related to legal accountability and convictions

    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
    iegel
    -0.19
    apur
    -0.13
    utzer
    -0.13
     обÑıзаÑĤелÑĮ
    -0.13
     Journey
    -0.13
    athy
    -0.13
    -ม
    -0.13
     ascending
    -0.13
    ãĥªãĤ¹
    -0.12
     showAlert
    -0.12
    POSITIVE LOGITS
     charges
    0.46
     trial
    0.43
     charge
    0.42
     conviction
    0.38
     charged
    0.38
     convictions
    0.37
     charging
    0.37
    trial
    0.36
     trials
    0.35
     guilty
    0.35
    Activations Density 0.007%

    No Known Activations