© 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. 55310
    Prev
    Next
    INDEX
    Explanations

    references to online competition and social media interactions

    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
    errals
    -0.17
    оваÑĢ
    -0.15
    xon
    -0.14
    óm
    -0.14
    aqu
    -0.14
    ople
    -0.14
     wsz
    -0.14
    éli
    -0.14
    erli
    -0.14
     Emails
    -0.14
    POSITIVE LOGITS
     post
    0.42
     posting
    0.41
    -post
    0.39
     posted
    0.35
     poste
    0.34
     Post
    0.33
    .post
    0.33
     shared
    0.33
    post
    0.32
     sharing
    0.32
    Activations Density 0.114%

    No Known Activations