© 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. 41963
    Prev
    Next
    INDEX
    Explanations

    references to user-generated content and its moderation

    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
    irc
    -0.15
    itin
    -0.14
    anko
    -0.13
    stown
    -0.13
     Prev
    -0.13
    /Data
    -0.13
     irc
    -0.13
    aho
    -0.13
    eba
    -0.13
    ognito
    -0.12
    POSITIVE LOGITS
     content
    1.06
    content
    0.84
     Content
    0.81
    -content
    0.74
    Content
    0.74
     CONTENT
    0.73
     contents
    0.71
    _content
    0.70
    åĨħ容
    0.69
    .content
    0.65
    Activations Density 0.114%

    No Known Activations