© 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. 909
    Prev
    Next
    INDEX
    Explanations

    time in centuries

    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
    soever
    -0.10
     Toll
    -0.10
     wholes
    -0.10
    'gc
    -0.09
    нÑĸÑģÑĤÑĮ
    -0.09
    年代
    -0.09
    afi
    -0.09
    ays
    -0.09
    etch
    -0.08
    mdb
    -0.08
    POSITIVE LOGITS
    -old
    0.21
    -long
    0.17
     ago
    0.16
     ÙħÛĮÙĦادÛĮ
    0.15
    aire
    0.14
     AD
    0.13
    -span
    0.12
    naire
    0.12
    ial
    0.12
    ago
    0.12
    Activations Density 0.043%

    No Known Activations