© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 22455
    Prev
    Next
    INDEX
    Explanations

    expressions of inclusion and examples in a structured context

    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
    orer
    -0.14
    	fflush
    -0.13
    ixo
    -0.13
    itect
    -0.13
    quil
    -0.13
    ãĥ³ãĥIJ
    -0.13
    é§
    -0.12
    .ribbon
    -0.12
    oi
    -0.12
    boru
    -0.12
    POSITIVE LOGITS
     example
    0.89
     examples
    0.80
    example
    0.72
     Example
    0.70
    Example
    0.67
     Examples
    0.66
     exemple
    0.63
    -example
    0.62
     ejemplo
    0.62
     EXAMPLE
    0.61
    Activations Density 0.040%

    No Known Activations