© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43426
    Prev
    Next
    INDEX
    Explanations

    commas followed by conjunctions

    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
     IonicModule
    -0.10
    ï¿¥
    -0.09
     Wein
    -0.09
    iry
    -0.09
    ï¼ł
    -0.08
    ãĢģ​
    -0.08
    oenix
    -0.08
    ););\n
    -0.08
    qus
    -0.08
    :maj
    -0.08
    POSITIVE LOGITS
     And
    0.11
    And
    0.10
    ë¥´ê³ł
    0.09
     à¹ģละ
    0.09
     VÃł
    0.08
     aftermath
    0.08
    ì§Ģê³ł
    0.08
    ãģĿãģĹãģ¦
    0.08
     Plat
    0.07
     ìŀĪê³ł
    0.07
    Activations Density 0.058%

    No Known Activations