© 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. 33104
    Prev
    Next
    INDEX
    Explanations

    dates and associated numerical data

    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
     Christmas
    -0.26
    Christmas
    -0.25
     christmas
    -0.21
     Merry
    -0.20
    itti
    -0.18
     December
    -0.15
    December
    -0.15
    axter
    -0.15
     Toys
    -0.15
    çĶ
    -0.14
    POSITIVE LOGITS
    Feb
    0.42
     Feb
    0.42
    February
    0.40
     Valentine
    0.36
     February
    0.36
    feb
    0.32
     Valent
    0.30
    -Feb
    0.28
     ÑĦев
    0.24
     val
    0.24
    Activations Density 0.024%

    No Known Activations