© 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. 29581
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or contrasts

    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
    ÑĢиз
    -0.15
     creampie
    -0.15
    ullets
    -0.15
    Ãły
    -0.15
    ude
    -0.14
    oldt
    -0.14
    lish
    -0.14
    artin
    -0.14
    ór
    -0.13
    аÑĤо
    -0.13
    POSITIVE LOGITS
     next
    0.78
    next
    0.63
    Next
    0.57
     Next
    0.57
     nächsten
    0.55
    .next
    0.54
    _next
    0.53
     näch
    0.53
     NEXT
    0.53
    -next
    0.52
    Activations Density 0.045%

    No Known Activations