© 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. 21099
    Prev
    Next
    INDEX
    Explanations

    a/an/another/two/several/multiple

    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
     eiusmod
    -0.10
    <|begin_of_text|>
    -0.09
     ragaz
    -0.09
    inyin
    -0.08
    )arg
    -0.08
    æľīä¸Ģ
    -0.08
     chtÄĽ
    -0.08
    IIIK
    -0.08
     dostan
    -0.08
    JNI
    -0.07
    POSITIVE LOGITS
     a
    0.20
     an
    0.19
     another
    0.15
    a
    0.14
     two
    0.13
     several
    0.12
    an
    0.12
     multiple
    0.12
    ä¸Ģ个人
    0.11
    another
    0.10
    Activations Density 0.372%

    No Known Activations