© 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 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. 28101
    Prev
    Next
    INDEX
    Explanations

    references to sexual assault and related investigations

    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
    isman
    -0.15
    icari
    -0.14
    δί
    -0.14
    ÑĤаж
    -0.14
    apesh
    -0.14
    ç¥ĸ
    -0.14
    elsen
    -0.13
    aira
    -0.13
    arian
    -0.13
    lek
    -0.13
    POSITIVE LOGITS
     cases
    0.26
    cases
    0.24
     prevention
    0.23
     awareness
    0.21
     Awareness
    0.21
     Prevention
    0.20
    _cases
    0.19
     victims
    0.18
     case
    0.18
     Cases
    0.17
    Activations Density 0.054%

    No Known Activations