© 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
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 37983
    Prev
    Next
    INDEX
    Explanations

    inventories and indemnification

    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
     Rosenberg
    -0.10
    æī£
    -0.10
     Amar
    -0.09
    ceipt
    -0.09
     Wolff
    -0.09
    _Object
    -0.09
    ï½²
    -0.09
    uala
    -0.08
     accounting
    -0.08
     NotImplemented
    -0.08
    POSITIVE LOGITS
     rece
    0.19
     Li
    0.17
    rece
    0.15
     invent
    0.15
     Rece
    0.15
     short
    0.14
    Li
    0.13
     liabilities
    0.13
     Invent
    0.13
     int
    0.12
    Activations Density 0.039%

    No Known Activations