© 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. 40803
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to changes or transitions in state or condition

    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
    å¤ķ
    -0.14
    -next
    -0.14
    NEXT
    -0.14
     навеÑĢ
    -0.14
     next
    -0.14
    olini
    -0.14
    uther
    -0.13
     NEXT
    -0.13
    chwitz
    -0.13
    conti
    -0.13
    POSITIVE LOGITS
     mid
    0.60
     middle
    0.47
    mid
    0.47
     Mid
    0.44
     midpoint
    0.44
     half
    0.42
     midterm
    0.41
    ä¸Ń
    0.41
     halfway
    0.40
    åįĬ
    0.40
    Activations Density 0.014%

    No Known Activations