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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38902
    Prev
    Next
    INDEX
    Explanations

    Canadian northern wilderness

    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
     Danish
    -0.12
    .dk
    -0.12
     Iowa
    -0.11
    avad
    -0.10
     Hansen
    -0.09
     slips
    -0.09
     dansk
    -0.09
    oplan
    -0.09
     Antique
    -0.09
     Flem
    -0.09
    POSITIVE LOGITS
     rein
    0.33
     Lap
    0.24
     northern
    0.21
     Northern
    0.20
     Arctic
    0.19
     bore
    0.18
     Trom
    0.18
     Aurora
    0.17
     aur
    0.16
     polar
    0.15
    Activations Density 0.025%

    No Known Activations