© 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. 42844
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    pyx
    -0.09
     böylece
    -0.08
     lion
    -0.08
    arcer
    -0.08
    kins
    -0.08
    CHAN
    -0.08
    ucus
    -0.08
    ingers
    -0.08
    orp
    -0.08
     pie
    -0.07
    POSITIVE LOGITS
     due
    0.61
    due
    0.52
     Due
    0.48
    çĶ±äºİ
    0.47
    Due
    0.46
     بسبب
    0.46
    åĽł
    0.44
     because
    0.43
     debido
    0.42
     kvůli
    0.42
    Activations Density 0.553%

    No Known Activations