© 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. 25186
    Prev
    Next
    INDEX
    Explanations

    references to actions involving getting into and riding in vehicles

    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
    oms
    -0.15
     Extension
    -0.14
     repmat
    -0.14
    ndl
    -0.14
     ÐľÐ¾Ñģква
    -0.14
    isEnabled
    -0.14
    ermen
    -0.14
     anchored
    -0.14
    andy
    -0.14
    urse
    -0.14
    POSITIVE LOGITS
     hop
    0.40
     climb
    0.37
     climbed
    0.36
    Hop
    0.35
     Hop
    0.33
     hopping
    0.33
     board
    0.33
     climbing
    0.32
     hops
    0.32
     jump
    0.32
    Activations Density 0.014%

    No Known Activations