© 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. 41701
    Prev
    Next
    INDEX
    Explanations

    instances of text formatting or syntax in programming or markup languages

    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
    ÙĪسÛĮ
    -0.13
    ÄĽk
    -0.13
    EntryPoint
    -0.13
    ê¶ģ
    -0.13
    _SF
    -0.13
    .:.:
    -0.12
    à¹Ħหà¸Ļ
    -0.12
    .TODO
    -0.12
     Чи
    -0.12
    NamedQuery
    -0.12
    POSITIVE LOGITS
    eldorf
    0.17
    odiac
    0.15
     Guerrero
    0.14
    .Imaging
    0.14
    urette
    0.13
     Escorts
    0.13
    ellido
    0.13
    ordova
    0.13
    çĢ¬
    0.13
     activeClassName
    0.13
    Activations Density 0.000%

    No Known Activations