© 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. 37126
    Prev
    Next
    INDEX
    Explanations

    ãĤĴä½ľ followed by ãĤģ or ãĤĬ

    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
    ãĤīãģĹ
    -0.12
    ãĤĿ
    -0.11
    ãĤıãĤĮ
    -0.10
    ãģĹãģªãģĦ
    -0.10
    ãģĭãģªãģĦ
    -0.09
    ãģijãĤĮãģ°
    -0.09
    ãĤŀ
    -0.09
    ãģŁãģ¡ãģ®
    -0.09
    ãĤīãģĽ
    -0.09
    ãĤıãĤĮãģŁ
    -0.09
    POSITIVE LOGITS
    ķãĤĵ
    0.10
    eba
    0.10
    ãģĺ
    0.09
    åIJ¦
    0.09
    dex
    0.09
    áÄį
    0.09
    mui
    0.09
    ãģĦ
    0.09
     Gregg
    0.09
    639
    0.09
    Activations Density 0.039%

    No Known Activations