© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 3454
    Prev
    Next
    INDEX
    Explanations

    decided to take action

    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
    finder
    -0.10
     berhasil
    -0.09
    ugu
    -0.09
    lest
    -0.09
    rin
    -0.09
    ãĥ¼ãĤ¯
    -0.09
     Jonas
    -0.09
    697
    -0.09
    VOID
    -0.08
    cho
    -0.08
    POSITIVE LOGITS
     test
    0.13
     take
    0.11
    ober
    0.10
     bet
    0.10
     fate
    0.10
     thá»Ń
    0.09
     prendre
    0.09
     challeng
    0.09
    oyer
    0.09
    -ÑĤаки
    0.09
    Activations Density 0.046%

    No Known Activations