© 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. 62332
    Prev
    Next
    INDEX
    Explanations

    she's or i've

    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
    rror
    -0.10
    éĮ
    -0.09
    quine
    -0.09
     Fuse
    -0.09
    916
    -0.09
    åĭ
    -0.09
    icari
    -0.09
    onte
    -0.09
    .BigDecimal
    -0.08
    ä¸įå¾Ĺ
    -0.08
    POSITIVE LOGITS
     too
    0.16
    åıªè¦ģ
    0.13
    too
    0.12
     busy
    0.12
    Too
    0.12
    Busy
    0.12
     Too
    0.11
     Nor
    0.11
    åıį
    0.10
     demasi
    0.10
    Activations Density 0.027%

    No Known Activations