© 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. 29933
    Prev
    Next
    INDEX
    Explanations

    organize better

    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
     ï½°
    -0.09
     uninterrupted
    -0.09
     superiority
    -0.08
    podob
    -0.08
     hardest
    -0.08
     proven
    -0.08
     weaker
    -0.08
     поба
    -0.08
     unfavor
    -0.08
    ìŀ¡ëĭ´
    -0.08
    POSITIVE LOGITS
     better
    0.26
    better
    0.21
     лÑĥÑĩÑĪе
    0.19
     besser
    0.19
     melhor
    0.19
     mejor
    0.18
    æĽ´åĬł
    0.17
     maximum
    0.16
    ãĤĪãĤĬ
    0.16
     بÙĩتر
    0.16
    Activations Density 0.134%

    No Known Activations