© 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. 49918
    Prev
    Next
    INDEX
    Explanations

    work/action followed by conjunction/preposition

    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
     penet
    -0.09
    wort
    -0.09
     Thou
    -0.08
    loub
    -0.08
    ä¹ĭä¸Ģ
    -0.08
    彡
    -0.08
    xda
    -0.08
     totalement
    -0.08
     SCE
    -0.08
     thou
    -0.08
    POSITIVE LOGITS
    ativ
    0.13
    tran
    0.11
     con
    0.10
     indem
    0.10
     ​​
    0.10
     gratis
    0.09
    aternity
    0.09
    lass
    0.09
    omic
    0.09
     harder
    0.09
    Activations Density 0.156%

    No Known Activations