© 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. 35093
    Prev
    Next
    INDEX
    Explanations

    dimensions (width, height)

    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
    ioso
    -0.11
    azzi
    -0.10
    AYOUT
    -0.09
     XT
    -0.09
    волÑı
    -0.09
     faiz
    -0.09
    adh
    -0.09
    надлеж
    -0.09
     Carr
    -0.08
    .pageY
    -0.08
    POSITIVE LOGITS
    800
    0.20
    400
    0.18
    640
    0.16
    300
    0.16
    500
    0.16
    600
    0.15
    100
    0.13
    700
    0.12
    inx
    0.12
    150
    0.11
    Activations Density 0.032%

    No Known Activations