© 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. 28172
    Prev
    Next
    INDEX
    Explanations

    descriptors and conditions

    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
    -0.24
    ï¼Įä½Ĩ
    -0.20
     nhÆ°ng
    -0.20
    ãģ§ãģĻãģĮ
    -0.19
     pero
    -0.19
     à¹ģà¸ķ
    -0.18
     ÙĪÙĦÙĥÙĨ
    -0.18
    ï¼Įä½Ĩæĺ¯
    -0.17
    ãģłãģĮ
    -0.17
     ÙĦÙĥÙĨ
    -0.17
    POSITIVE LOGITS
    åį»
    0.16
    åį´
    0.15
     Butt
    0.13
     butt
    0.12
     none
    0.12
     thanks
    0.12
    è¿ĺæĺ¯
    0.11
    theless
    0.11
     because
    0.11
    noch
    0.10
    Activations Density 0.218%

    No Known Activations