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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21656
    Prev
    Next
    INDEX
    Explanations

    percentage shares, commission fees

    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
    財
    -0.10
     Commod
    -0.10
    丶
    -0.10
    ofilm
    -0.09
     CType
    -0.09
     commod
    -0.09
     roman
    -0.09
     Bain
    -0.08
     uncomp
    -0.08
     egreg
    -0.08
    POSITIVE LOGITS
     brut
    0.15
     charges
    0.14
     amount
    0.12
     charged
    0.12
     bonus
    0.12
     fee
    0.11
    charged
    0.11
    é¢Ŀ
    0.11
     Mens
    0.11
     mens
    0.11
    Activations Density 0.149%

    No Known Activations