© 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 EvalsExportsinterp-engineNEWAPI 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. 13152
    Prev
    Next
    INDEX
    Explanations

    references to states of emergency and disaster declarations

    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
    ilim
    -0.16
    dx
    -0.16
     Dixon
    -0.16
    Dot
    -0.15
    ARIANT
    -0.15
    UDO
    -0.14
    ys
    -0.14
    ¬¬
    -0.14
    asticsearch
    -0.14
    din
    -0.14
    POSITIVE LOGITS
     declaration
    1.10
     declare
    1.00
     Decl
    0.99
     declared
    0.98
     Declaration
    0.98
     declarations
    0.97
     Declare
    0.91
     declaring
    0.90
     declares
    0.87
     DECL
    0.87
    Activations Density 0.010%

    No Known Activations