© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 38089
    Prev
    Next
    INDEX
    Explanations

    subject introduced by who

    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
    ubs
    -0.09
    ãĢĢï¾ī
    -0.09
    indo
    -0.09
    (where
    -0.08
     Fulton
    -0.08
    492
    -0.08
     ознаÑĩа
    -0.08
    orf
    -0.08
     {.
    -0.08
    æľīä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
     who
    0.57
    who
    0.44
     whose
    0.37
     quien
    0.37
     whom
    0.33
     quienes
    0.29
     qui
    0.28
    whose
    0.28
     اÙĦØ°ÙĬÙĨ
    0.27
     kteÅĻÃŃ
    0.27
    Activations Density 0.144%

    No Known Activations