© 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. 44553
    Prev
    Next
    INDEX
    Explanations

    multilingual punctuation and word fragments

    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
    xeb
    -0.08
    ć
    -0.08
    μοί
    -0.08
    areth
    -0.08
    /stdc
    -0.08
    \tCopyright
    -0.08
    nů
    -0.08
     recept
    -0.08
    ocities
    -0.08
     cứ
    -0.08
    POSITIVE LOGITS
     [_
    0.12
    (sp
    0.11
    ï¾ŀ
    0.11
     versa
    0.10
    que
    0.09
    (?
    0.09
     [=
    0.09
    ://
    0.09
    /by
    0.08
    ingly
    0.08
    Activations Density 0.362%

    No Known Activations