© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44570
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to software, installation, and setup processes

    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
    lic
    -0.17
     лиÑĪ
    -0.14
    ifter
    -0.14
    steder
    -0.13
    æ¢
    -0.13
    宿
    -0.13
    ħn
    -0.13
     Lev
    -0.13
    rale
    -0.13
    958
    -0.12
    POSITIVE LOGITS
     mode
    0.69
     modes
    0.59
     Mode
    0.59
    mode
    0.55
    Mode
    0.54
    _mode
    0.52
     Modes
    0.52
    -mode
    0.51
    .mode
    0.49
    modes
    0.46
    Activations Density 0.023%

    No Known Activations