© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23806
    Prev
    Next
    INDEX
    Explanations

    terms associated with transportation and movement

    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
    letcher
    -0.19
    _walk
    -0.19
     Walk
    -0.19
     walk
    -0.17
    .walk
    -0.16
     walker
    -0.16
    ordova
    -0.15
     Aircraft
    -0.15
    Walk
    -0.15
     walkers
    -0.15
    POSITIVE LOGITS
     carrying
    0.21
     operating
    0.20
     traveling
    0.20
    è¼ī
    0.19
     rum
    0.19
    åģľ
    0.19
     driven
    0.19
    驶
    0.19
     operate
    0.19
    ply
    0.19
    Activations Density 0.078%

    No Known Activations