© 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. 58775
    Prev
    Next
    INDEX
    Explanations

    the word before specific nouns

    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
    isser
    -0.10
    ÄįasÃŃ
    -0.09
     výše
    -0.09
    以ä¸Ĭ
    -0.09
     yukarı
    -0.08
     Couple
    -0.08
    ptrdiff
    -0.08
    resh
    -0.08
    zik
    -0.08
     Monk
    -0.08
    POSITIVE LOGITS
     latter
    0.18
     same
    0.15
    該
    0.15
     said
    0.15
    该
    0.14
     tersebut
    0.14
     íķ´ëĭ¹
    0.13
     thereof
    0.12
    å®ĥ
    0.12
     Äijó
    0.11
    Activations Density 0.265%

    No Known Activations