© 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. 13598
    Prev
    Next
    INDEX
    Explanations

    being or state of being

    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
     dapat
    -0.11
     possono
    -0.10
     pueden
    -0.10
    could
    -0.10
     могла
    -0.10
     peuvent
    -0.10
     kunnen
    -0.10
     могли
    -0.10
    Could
    -0.09
     सà¤ķत
    -0.09
    POSITIVE LOGITS
     Äijang
    0.31
     befind
    0.31
     наÑħодиÑĤÑģÑı
    0.29
    æŃ£åľ¨
    0.26
    å¤Ħ
    0.23
     está
    0.20
     estar
    0.20
     наÑħод
    0.18
     estava
    0.17
    à¸Ńย
    0.17
    Activations Density 0.229%

    No Known Activations