© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38764
    Prev
    Next
    INDEX
    Explanations

    must or will follow subjects

    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
    ãĤ¡
    -0.12
     можно
    -0.11
     gonna
    -0.10
     można
    -0.10
    could
    -0.10
     could
    -0.10
     Fist
    -0.09
     bisa
    -0.09
    ä¸įåŃĺåľ¨
    -0.09
     gan
    -0.09
    POSITIVE LOGITS
     must
    0.21
    å¿ħé¡»
    0.18
     phải
    0.18
    must
    0.16
     required
    0.16
     müssen
    0.14
     deben
    0.14
    é¡»
    0.14
     responsible
    0.13
     musÃŃ
    0.13
    Activations Density 0.056%

    No Known Activations