© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54339
    Prev
    Next
    INDEX
    Explanations

    references to the founding principles and intentions of the U.S. government

    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
    GenerationStrategy
    -0.16
    éĺħ读次æķ°
    -0.16
    OffsetTable
    -0.15
    UsageId
    -0.14
    à¸Ħรà¸ļ
    -0.14
    jejer
    -0.13
     ÙĪØ²Ø§Ø±
    -0.13
    //{{
    -0.13
    /assert
    -0.13
    _restore
    -0.13
    POSITIVE LOGITS
     design
    0.19
     draft
    0.18
     fores
    0.17
     compromises
    0.17
     compromise
    0.17
     ORIGINAL
    0.17
     establishing
    0.17
     drafting
    0.17
    设计
    0.17
     vision
    0.17
    Activations Density 0.032%

    No Known Activations