© 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. 160
    Prev
    Next
    INDEX
    Explanations

    such as bypass

    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
    å®Ļ
    -0.09
     typical
    -0.09
    rea
    -0.09
    iem
    -0.09
    681
    -0.09
     Berm
    -0.09
     richt
    -0.09
    tram
    -0.08
    rowable
    -0.08
     Hank
    -0.08
    POSITIVE LOGITS
     situations
    0.13
     напÑĢимеÑĢ
    0.12
     testing
    0.11
     ÙħØ«ÙĦا
    0.11
    æĸ¹
    0.11
     legacy
    0.11
    æŁIJ
    0.11
    legacy
    0.10
     Testing
    0.10
    -testing
    0.10
    Activations Density 0.142%

    No Known Activations