© 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. 33100
    Prev
    Next
    INDEX
    Explanations

    references to travel experiences and locations

    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
    íķĺìĦ¸ìļĶ
    -0.17
    racÃŃ
    -0.15
     ä»ĸ
    -0.15
     lately
    -0.14
     his
    -0.14
     há»į
    -0.14
     eÄŁer
    -0.13
     recently
    -0.13
    itesse
    -0.13
    æľĢè¿ij
    -0.12
    POSITIVE LOGITS
     ourselves
    0.41
     we
    0.39
     our
    0.37
    æĪij们
    0.31
    æĪijåĢij
    0.30
     ours
    0.29
     my
    0.28
     myself
    0.28
    we
    0.27
    æĪij们çļĦ
    0.27
    Activations Density 0.227%

    No Known Activations