© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63691
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial costs or expenses

    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
    VML
    -0.18
    eniable
    -0.15
     Merrill
    -0.14
    rai
    -0.14
    ecycle
    -0.14
    enberg
    -0.14
    fir
    -0.14
    aye
    -0.13
     Voll
    -0.13
    _utf
    -0.13
    POSITIVE LOGITS
     money
    0.31
    money
    0.24
     MONEY
    0.23
     than
    0.22
     Money
    0.21
    Money
    0.21
    -money
    0.21
    éĴ±
    0.21
     dinero
    0.20
     per
    0.19
    Activations Density 0.056%

    No Known Activations