© 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. 58788
    Prev
    Next
    INDEX
    Explanations

    najważniejsze, most important

    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
    sembly
    -0.11
    rint
    -0.11
    ëł¹
    -0.11
     [[]
    -0.10
    าà¸Ńย
    -0.10
     Lowest
    -0.09
    427
    -0.09
    ivÄĽ
    -0.09
     cum
    -0.08
    lâm
    -0.08
    POSITIVE LOGITS
     hơn
    0.31
    нее
    0.24
    niejs
    0.22
    er
    0.21
    nÄĽjÅ¡ÃŃ
    0.21
    αλÏįÏĦε
    0.20
    lier
    0.20
    ÏĮÏĦε
    0.20
    ÄĽjÅ¡ÃŃ
    0.19
     more
    0.17
    Activations Density 0.072%

    No Known Activations