© 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. 53989
    Prev
    Next
    INDEX
    Explanations

    actions related to travel or movement, particularly boarding a plane

    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
    иÑĨ
    -0.17
    dock
    -0.16
    borough
    -0.16
    _CE
    -0.15
     تÙĤÙĪ
    -0.14
    VIC
    -0.14
    .gateway
    -0.14
    олоÑĪ
    -0.14
    ,unsigned
    -0.14
     Entr
    -0.13
    POSITIVE LOGITS
     plane
    0.56
     train
    0.45
    plane
    0.43
     Plane
    0.43
     planes
    0.42
    Plane
    0.40
     bus
    0.37
     flight
    0.37
    -plane
    0.36
     airplane
    0.36
    Activations Density 0.056%

    No Known Activations