© 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. 31237
    Prev
    Next
    INDEX
    Explanations

    breakthrough

    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
    via
    -0.11
    ãĥķãĤ
    -0.09
     Paula
    -0.09
     Via
    -0.09
     intercept
    -0.09
     via
    -0.09
     overhead
    -0.09
    Via
    -0.09
    .Restrict
    -0.09
     ìĸ¼
    -0.08
    POSITIVE LOGITS
     breakthrough
    0.28
    ç©¿
    0.25
     break
    0.24
    çł´
    0.24
     bre
    0.23
     пÑĢоÑĢ
    0.22
     breach
    0.21
     bypass
    0.21
     breaking
    0.20
     Break
    0.20
    Activations Density 0.094%

    No Known Activations