© 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. 22879
    Prev
    Next
    INDEX
    Explanations

    phrases related to the physical condition of animals

    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
    ots
    -0.16
    áž
    -0.14
     seni
    -0.13
     gaz
    -0.13
    tain
    -0.13
    ëĵĿ
    -0.13
     voks
    -0.13
     Patterns
    -0.13
     runaway
    -0.13
    еви
    -0.13
    POSITIVE LOGITS
     shape
    0.64
     condition
    0.54
     Shape
    0.51
    shape
    0.50
     Condition
    0.43
    Shape
    0.41
    condition
    0.40
     shapes
    0.38
    Condition
    0.37
    .shape
    0.37
    Activations Density 0.022%

    No Known Activations