© 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. 29640
    Prev
    Next
    INDEX
    Explanations

    comparisons related to digital platforms and their functionality

    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
    igrations
    -0.15
    afx
    -0.15
    ARCH
    -0.15
    aque
    -0.14
    galement
    -0.14
    aret
    -0.14
    imu
    -0.13
     unsubscribe
    -0.13
    äd
    -0.13
    phem
    -0.13
    POSITIVE LOGITS
     Wikipedia
    0.62
     wiki
    0.60
    wiki
    0.60
     Wiki
    0.58
    Wiki
    0.54
    .wikipedia
    0.53
     wikipedia
    0.52
     Wikimedia
    0.51
    /wiki
    0.49
    Wik
    0.48
    Activations Density 0.016%

    No Known Activations