© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24143
    Prev
    Next
    INDEX
    Explanations

    references to drugs and their effects, particularly in relation to legality and conditions of use

    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
    yses
    -0.16
    ede
    -0.15
    è¿«
    -0.15
    yp
    -0.14
    azzo
    -0.14
    mez
    -0.14
    .sax
    -0.14
    emons
    -0.14
    вол
    -0.14
    Malloc
    -0.14
    POSITIVE LOGITS
     substances
    0.48
     substance
    0.42
     drugs
    0.41
     Substance
    0.33
     drug
    0.31
     Drugs
    0.30
     psycho
    0.24
    -dr
    0.24
    -il
    0.23
     chemicals
    0.23
    Activations Density 0.064%

    No Known Activations