© 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 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. 42611
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or events

    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
    onne
    -0.17
    ce
    -0.15
    336
    -0.14
    271
    -0.14
    usal
    -0.14
    ast
    -0.14
    forth
    -0.14
    129
    -0.13
    833
    -0.13
    55
    -0.13
    POSITIVE LOGITS
    90
    0.32
    80
    0.31
    198
    0.26
     nin
    0.25
    70
    0.24
    199
    0.24
    å¹³æĪIJ
    0.20
    eties
    0.20
    ught
    0.20
    197
    0.20
    Activations Density 0.040%

    No Known Activations