© 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. 5037
    Prev
    Next
    INDEX
    Explanations

    reason, you your he

    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
     zwar
    -0.14
     despite
    -0.11
    ãģĵãģĿ
    -0.11
     Jord
    -0.10
     Might
    -0.10
     Mond
    -0.10
    óz
    -0.09
     indeed
    -0.09
    ym
    -0.09
    기ëıĦ
    -0.09
    POSITIVE LOGITS
    à¹ĩà¸ķาม
    0.14
     still
    0.13
     remains
    0.12
    åıªè¦ģ
    0.12
    still
    0.12
    éĥ½ä¼ļ
    0.12
    ult
    0.11
     ultimately
    0.11
     always
    0.10
     Äijá»ģu
    0.10
    Activations Density 0.050%

    No Known Activations