© 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. 57686
    Prev
    Next
    INDEX
    Explanations

    Korean, Turkish, or code blocks

    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
     yoktu
    -0.11
     olmam
    -0.11
    idges
    -0.10
     definitely
    -0.09
    ëĿ¼ëıĦ
    -0.09
     Horde
    -0.08
    adors
    -0.08
    arding
    -0.08
     olduk
    -0.08
    837
    -0.08
    POSITIVE LOGITS
    ardır
    0.21
     ÑıвлÑıеÑĤÑģÑı
    0.18
    udur
    0.18
    ìĿ´ëĭ¤
    0.18
    ãģ§ãģĤãĤĭ
    0.17
    esidir
    0.17
    lardır
    0.17
    idir
    0.17
     ê²ĥìĿ´ëĭ¤
    0.16
     باشد
    0.16
    Activations Density 0.119%

    No Known Activations