© 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. 15834
    Prev
    Next
    INDEX
    Explanations

    instances of discovery or realization in the context of personal experiences

    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
    iku
    -0.16
    imo
    -0.14
     pretend
    -0.14
    nk
    -0.14
    æľĿ
    -0.14
    lems
    -0.13
     throughout
    -0.13
     tension
    -0.13
     sadly
    -0.13
    ohon
    -0.13
    POSITIVE LOGITS
     chance
    0.49
     Chance
    0.36
    Chance
    0.32
     ÑģлÑĥÑĩай
    0.31
     accident
    0.29
     coinc
    0.29
    åģ¶
    0.28
     ser
    0.28
     chances
    0.27
     випад
    0.26
    Activations Density 0.072%

    No Known Activations