© 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. 36687
    Prev
    Next
    INDEX
    Explanations

    by, through, via

    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
     Bye
    -0.13
     indirect
    -0.09
    upd
    -0.09
     finally
    -0.08
     Byron
    -0.08
    ìĹĨìĿ´
    -0.08
    >(*
    -0.08
     Byrne
    -0.08
     Loch
    -0.08
    verbatim
    -0.08
    POSITIVE LOGITS
     via
    0.49
     пÑĥÑĤем
    0.45
     through
    0.41
    via
    0.38
     mediante
    0.35
     ÑĪлÑıÑħом
    0.33
    éĢļè¿ĩ
    0.32
    through
    0.29
     durch
    0.29
     prostÅĻednictvÃŃm
    0.28
    Activations Density 0.295%

    No Known Activations