© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29174
    Prev
    Next
    INDEX
    Explanations

    financial terms and metrics related to company performance

    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
    allet
    -0.19
     Panc
    -0.17
    ãĥ³ãĥģ
    -0.14
    ç§
    -0.14
    rocket
    -0.14
     Dag
    -0.14
     bars
    -0.13
     rocket
    -0.13
     panc
    -0.13
    AEA
    -0.13
    POSITIVE LOGITS
     dividend
    0.47
     dividends
    0.41
     Div
    0.40
    Div
    0.37
     divid
    0.33
     div
    0.33
    -div
    0.31
     див
    0.31
    /div
    0.30
    divid
    0.30
    Activations Density 0.017%

    No Known Activations