© 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. 28478
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate instructions or prompts to engage with content

    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
    ï¿
    -0.12
    ãĥ³ãĥij
    -0.12
    ovan
    -0.12
     reklam
    -0.12
    ista
    -0.12
    eb
    -0.12
    ç§ģãģ®
    -0.12
    iÅŁ
    -0.11
    ç½
    -0.11
    :I
    -0.11
    POSITIVE LOGITS
     check
    0.23
     tune
    0.22
     Check
    0.19
    Check
    0.18
     keep
    0.18
     stay
    0.18
     stayed
    0.18
    check
    0.18
     checking
    0.17
     tunes
    0.17
    Activations Density 0.188%

    No Known Activations