© 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. 34564
    Prev
    Next
    INDEX
    Explanations

    exemples

    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
     Tig
    -0.09
     Uy
    -0.09
    bigint
    -0.09
     Nep
    -0.09
     armed
    -0.09
    æİĮ
    -0.09
    emed
    -0.09
    ita
    -0.08
     recru
    -0.08
     conseils
    -0.08
    POSITIVE LOGITS
     applications
    0.10
     Leone
    0.10
    ossible
    0.10
     plate
    0.10
    नल
    0.09
    InputBorder
    0.09
    çı
    0.09
    elyn
    0.09
     games
    0.09
     systems
    0.09
    Activations Density 0.249%

    No Known Activations