© 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. 37242
    Prev
    Next
    INDEX
    Explanations

    change and its consequences

    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
    iet
    -0.09
    anga
    -0.09
    Pont
    -0.09
    tml
    -0.08
    .TypeOf
    -0.08
    ثر
    -0.08
     Mant
    -0.08
     Neville
    -0.08
     zby
    -0.08
    ernet
    -0.08
    POSITIVE LOGITS
     rect
    0.37
     remedy
    0.28
     change
    0.28
     changed
    0.27
     Rect
    0.27
     remed
    0.25
    rect
    0.25
    æĶ¹åıĺ
    0.23
     changing
    0.22
    change
    0.21
    Activations Density 0.129%

    No Known Activations