© 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. 43862
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial implications and metrics within a business 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
    borough
    -0.15
    icut
    -0.15
    VED
    -0.14
    екаÑĢ
    -0.14
    eren
    -0.14
     Vog
    -0.14
    دÙĪ
    -0.13
     Evet
    -0.13
     Fletcher
    -0.13
    ernes
    -0.13
    POSITIVE LOGITS
     bottom
    0.60
     Bottom
    0.51
    bottom
    0.49
     BOTTOM
    0.47
    Bottom
    0.44
    -bottom
    0.40
    BOTTOM
    0.39
    .bottom
    0.33
     profits
    0.32
     bottoms
    0.32
    Activations Density 0.030%

    No Known Activations