© 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. 23812
    Prev
    Next
    INDEX
    Explanations

    represents strings or variables

    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
    ugin
    -0.10
    å¼¥
    -0.09
     Preferred
    -0.08
     seeming
    -0.08
    ù
    -0.08
    674
    -0.08
    inite
    -0.08
     Dread
    -0.08
     deserted
    -0.08
    estone
    -0.08
    POSITIVE LOGITS
     assumed
    0.19
     ê°Ģìłķ
    0.15
     assum
    0.15
     must
    0.15
    å¿ħé¡»
    0.15
     Ùģرض
    0.14
    must
    0.14
    åģĩ
    0.13
     Must
    0.13
    assume
    0.13
    Activations Density 0.117%

    No Known Activations