© 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. 29919
    Prev
    Next
    INDEX
    Explanations

    own strategies and advantages

    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
     disappoint
    -0.11
     even
    -0.11
     compared
    -0.10
     imperfect
    -0.10
    zilla
    -0.10
    æĹ¢
    -0.10
     opposed
    -0.09
     helping
    -0.09
     Compared
    -0.09
     rar
    -0.09
    POSITIVE LOGITS
     compens
    0.19
     compensate
    0.16
     compensated
    0.15
     advantage
    0.14
    ä¼ĺåĬ¿
    0.13
     compensation
    0.13
     advantages
    0.13
     strengths
    0.12
     still
    0.12
    still
    0.12
    Activations Density 0.068%

    No Known Activations