© 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. 41060
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ingo
    -0.16
    å³
    -0.16
    theros
    -0.15
    iche
    -0.15
    aries
    -0.14
    ç´į
    -0.14
    -mouth
    -0.14
    asad
    -0.14
    illance
    -0.14
    .dp
    -0.13
    POSITIVE LOGITS
    ities
    0.32
    ity
    0.27
     cleansing
    0.26
    ALLY
    0.25
    ITIES
    0.23
     minority
    0.23
    ally
    0.23
     minorities
    0.21
     Cleans
    0.21
    minor
    0.21
    Activations Density 0.010%

    No Known Activations