© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 22699
    Prev
    Next
    INDEX
    Explanations

    phrases related to identity and personal labels

    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
    imus
    -0.16
    .SwingConstants
    -0.15
    ulet
    -0.15
    åĦĢ
    -0.14
    VisualStyle
    -0.14
    ulumi
    -0.14
     wallpapers
    -0.14
     queryInterface
    -0.13
     vidéo
    -0.13
    ngine
    -0.13
    POSITIVE LOGITS
     words
    0.27
     writing
    0.23
     writings
    0.22
     inscription
    0.20
     ins
    0.19
    words
    0.19
     names
    0.19
     text
    0.19
     message
    0.18
     legend
    0.18
    Activations Density 0.051%

    No Known Activations