© 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. 13617
    Prev
    Next
    INDEX
    Explanations

    mentions of harmful substances and their effects

    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
    /Instruction
    -0.15
    âĢ¦↵
    -0.15
    Ìģ
    -0.13
    .âĢ¦
    -0.12
     именно
    -0.12
    âĢ¦
    -0.12
    ÌĢ
    -0.12
    ...↵
    -0.12
     milfs
    -0.12
    č
    -0.12
    POSITIVE LOGITS
    >tag
    0.17
     overall
    0.16
    htags
    0.14
    окÑĢем
    0.14
     ActionTypes
    0.14
     Overall
    0.13
     NVIC
    0.13
     outright
    0.13
    currentColor
    0.13
    ÐIJÑĢÑħÑĸв
    0.13
    Activations Density 0.017%

    No Known Activations