Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65008
    Prev
    Next
    INDEX
    Explanations

    company identification and tax data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fee
    -0.10
    fee
    -0.10
     fle
    -0.10
     Neptune
    -0.10
     fees
    -0.09
    sem
    -0.09
     Fee
    -0.09
    orsi
    -0.09
     Tol
    -0.09
     sem
    -0.09
    POSITIVE LOGITS
     taxpayer
    0.14
     tax
    0.13
    /Branch
    0.13
    vat
    0.12
     Tax
    0.11
    rej
    0.11
     VAT
    0.10
    elay
    0.10
    tax
    0.10
     mük
    0.10
    Activations Density 0.073%

    No Known Activations