© 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. 24681
    Prev
    Next
    INDEX
    Explanations

    return result

    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
     karak
    -0.08
    -dismissible
    -0.08
    ãģħ
    -0.08
    -hook
    -0.07
    ​\n\n
    -0.07
     ï
    -0.07
    bsd
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
    suz
    -0.07
    adin
    -0.07
    POSITIVE LOGITS
    .ActionListener
    0.10
    .toBe
    0.09
    ãģijãĤĮãģ©
    0.08
    ZD
    0.08
     [âĢ¦]\n\n
    0.07
     McA
    0.07
     Clair
    0.07
    izr
    0.07
     HttpServlet
    0.07
    ılıģıyla
    0.07
    Activations Density 0.266%

    No Known Activations