© 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. 14369
    Prev
    Next
    INDEX
    Explanations

    bottom

    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
     upstairs
    -0.16
    .ToUpper
    -0.13
     Above
    -0.13
    üstü
    -0.12
     üst
    -0.12
    toUpperCase
    -0.12
     upstream
    -0.12
    .toUpperCase
    -0.12
    Above
    -0.11
    above
    -0.11
    POSITIVE LOGITS
     lower
    0.50
     bottom
    0.50
     below
    0.42
    ä¸ĭ
    0.42
    bottom
    0.41
     ниж
    0.41
    åºķ
    0.40
     Bottom
    0.39
    Bottom
    0.38
    lower
    0.37
    Activations Density 0.164%

    No Known Activations