© 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. 32860
    Prev
    Next
    INDEX
    Explanations

    job titles and roles

    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
    ÐĴÑĤ
    -0.10
    ê±°ëĤĺ
    -0.09
    пÑĢимеÑĢ
    -0.09
     -*-č\n
    -0.09
     or
    -0.09
    ÂĢÂĢ
    -0.08
    ekim
    -0.08
    æĪĸ
    -0.08
    åĴĮ
    -0.08
     ê·¸ë¦¬ê³ł
    -0.08
    POSITIVE LOGITS
    uits
    0.09
    463
    0.08
     ​​
    0.08
     Handy
    0.08
    .pm
    0.08
    -related
    0.07
    658
    0.07
    ervations
    0.07
    ãģ¨ãģĦãģĨ
    0.07
    iaux
    0.07
    Activations Density 1.098%

    No Known Activations