© 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. 56147
    Prev
    Next
    INDEX
    Explanations

    centric approach or design

    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
    781
    -0.10
    RTC
    -0.09
    631
    -0.09
    ofs
    -0.09
    enze
    -0.09
    orama
    -0.09
    RTOS
    -0.09
    753
    -0.09
    endale
    -0.08
    xit
    -0.08
    POSITIVE LOGITS
     approach
    0.34
     Approach
    0.27
    appro
    0.23
     approached
    0.22
    Appro
    0.21
    ness
    0.19
     approaches
    0.17
     подÑħод
    0.17
     yaklaÅŁ
    0.16
    ity
    0.16
    Activations Density 0.027%

    No Known Activations