© 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. 9627
    Prev
    Next
    INDEX
    Explanations

    you, AI language model

    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
    achi
    -0.09
    kuk
    -0.09
    gom
    -0.08
    ivan
    -0.08
    unge
    -0.08
    igham
    -0.08
    Ñĩем
    -0.08
    âĺħ
    -0.08
     Beck
    -0.08
    [Test
    -0.08
    POSITIVE LOGITS
    ãĤ
    0.11
     taxpayer
    0.10
    aday
    0.10
    plural
    0.09
    ients
    0.09
    ve
    0.09
    Ｏ
    0.09
    zelf
    0.09
     à¸ģรà¸ģ
    0.09
    Ｋ
    0.09
    Activations Density 0.087%

    No Known Activations