© 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. 167
    Prev
    Next
    INDEX
    Explanations

    greeting or response preamble

    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
     Criminal
    -0.10
     criminal
    -0.09
    [,]
    -0.09
    Vir
    -0.08
    Tho
    -0.08
    (ok
    -0.08
    (ir
    -0.08
    $fdata
    -0.08
     ï¼İ
    -0.08
    enden
    -0.08
    POSITIVE LOGITS
     Nicol
    0.09
    exampleInput
    0.09
    âĢIJ'
    0.09
    ä¸įäºĨ
    0.08
    lech
    0.08
    öst
    0.08
    èķ
    0.08
    CLUDING
    0.08
    oice
    0.07
     DBG
    0.07
    Activations Density 0.114%

    No Known Activations