© 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. 13814
    Prev
    Next
    INDEX
    Explanations

    references to personal choices and rights related to drugs and mental health

    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
    kontakte
    -0.19
    rowable
    -0.16
     Bewert
    -0.15
    ãĥ³ãĤ¸
    -0.15
     springfox
    -0.15
    заб
    -0.15
    ngr
    -0.14
     Opportunities
    -0.14
    Ñģол
    -0.14
    ertino
    -0.14
    POSITIVE LOGITS
     choice
    0.99
    choice
    0.78
     Choice
    0.77
     choices
    0.72
    Choice
    0.70
    -choice
    0.70
     choose
    0.67
     CHO
    0.64
     cho
    0.63
    _choice
    0.63
    Activations Density 0.047%

    No Known Activations