© 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. 33445
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects of substance abuse and its consequences

    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
    \grid
    -0.15
    åĽ½ãģ®
    -0.14
    ajs
    -0.14
     BinaryTree
    -0.14
    ften
    -0.14
    GridColumn
    -0.14
    (^)(
    -0.14
    Warm
    -0.14
    .useState
    -0.14
    .dds
    -0.14
    POSITIVE LOGITS
     toll
    0.62
     Toll
    0.49
     tol
    0.33
     strain
    0.27
    oll
    0.24
     its
    0.23
     Tol
    0.23
     wear
    0.23
     strains
    0.22
    OLL
    0.21
    Activations Density 0.025%

    No Known Activations