© 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. 63448
    Prev
    Next
    INDEX
    Explanations

    commentary and exploration

    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
     juxtap
    -0.11
     contrad
    -0.09
    oltip
    -0.09
    pees
    -0.09
     controversies
    -0.09
     researcher
    -0.09
     paradox
    -0.09
     cigaret
    -0.08
     fighting
    -0.08
    æľĹ
    -0.08
    POSITIVE LOGITS
     explore
    0.21
    æİ¢
    0.21
     commentary
    0.21
     exploration
    0.20
     Explore
    0.19
     exploring
    0.18
     comment
    0.18
     explores
    0.18
    Explore
    0.17
     questions
    0.16
    Activations Density 0.049%

    No Known Activations