© 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. 29173
    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
     mashed
    -0.15
    //{{
    -0.15
    antan
    -0.14
    icari
    -0.14
     ìłIJ
    -0.14
     hammered
    -0.14
    ining
    -0.13
     nÄĥ
    -0.13
     shovel
    -0.13
    ammed
    -0.13
    POSITIVE LOGITS
     making
    0.24
    -making
    0.23
     make
    0.23
     membuat
    0.22
     Making
    0.22
    making
    0.22
     prepare
    0.22
     preparing
    0.22
     prepares
    0.22
     makes
    0.21
    Activations Density 0.097%

    No Known Activations