© 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. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44485
    Prev
    Next
    INDEX
    Explanations

    principal amount

    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
    ates
    -0.10
    eken
    -0.09
    ::_
    -0.09
    allet
    -0.09
     pled
    -0.08
     accr
    -0.08
    atch
    -0.08
    [url
    -0.08
     scal
    -0.08
     Estr
    -0.08
    POSITIVE LOGITS
     amount
    0.21
     principal
    0.20
     sum
    0.16
     value
    0.16
     Principal
    0.15
    amount
    0.15
    principal
    0.15
     price
    0.15
     Amount
    0.15
     balance
    0.14
    Activations Density 0.082%

    No Known Activations