© 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. 2554
    Prev
    Next
    INDEX
    Explanations

    programming and data manipulation

    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
    ìłĪ
    -0.10
     Bram
    -0.10
     lur
    -0.09
     []:\n
    -0.09
     setattr
    -0.09
    æĪª
    -0.09
    berman
    -0.09
     hereby
    -0.08
    QUEST
    -0.08
     Curtis
    -0.08
    POSITIVE LOGITS
     None
    0.13
     int
    0.12
    /=
    0.10
    None
    0.10
    OffsetTable
    0.10
    {}\n
    0.10
     {}\n
    0.09
    309
    0.09
     tolua
    0.09
     Heal
    0.09
    Activations Density 0.033%

    No Known Activations