© 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. 22827
    Prev
    Next
    INDEX
    Explanations

    terms associated with market dynamics and financial transactions

    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
    uguay
    -0.15
    ToOne
    -0.14
    .LayoutStyle
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.13
    gui
    -0.13
    .scalablytyped
    -0.13
    ificaciones
    -0.13
    maktan
    -0.13
    ullen
    -0.13
    neau
    -0.12
    POSITIVE LOGITS
    able
    1.10
    ability
    0.85
    ABLE
    0.81
    ables
    0.75
    ible
    0.70
     able
    0.70
    izable
    0.66
     Able
    0.63
    nable
    0.60
    gable
    0.59
    Activations Density 0.039%

    No Known Activations