© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24385
    Prev
    Next
    INDEX
    Explanations

    instances of social validation and approval within communities

    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
    IVEN
    -0.15
    tridge
    -0.14
    pires
    -0.14
    ož
    -0.14
     authDomain
    -0.14
     damer
    -0.14
     Dữ
    -0.14
    PPER
    -0.13
    ÙĨز
    -0.13
    -valu
    -0.13
    POSITIVE LOGITS
     âĢª
    0.17
    kla
    0.17
    gn
    0.15
    Ø·Ùģ
    0.14
    765
    0.13
    abh
    0.13
    OU
    0.13
     @
    0.13
    odont
    0.13
    PURE
    0.13
    Activations Density 0.085%

    No Known Activations