Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41482
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stand" or its variations

    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
    .bd
    -0.16
    ë¶Ģ
    -0.15
    baÅŁ
    -0.14
    culated
    -0.14
    apon
    -0.14
    اخر
    -0.14
    ured
    -0.14
    edo
    -0.14
    ymoon
    -0.14
     tabi
    -0.14
    POSITIVE LOGITS
    still
    0.21
    alone
    0.20
     alone
    0.17
    olle
    0.17
    -alone
    0.17
    adr
    0.16
     still
    0.15
    pose
    0.15
     behind
    0.15
     Alone
    0.15
    Activations Density 0.002%

    No Known Activations