© 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. 20810
    Prev
    Next
    INDEX
    Explanations

    offering another or new version

    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
     Hlav
    -0.11
    .Logic
    -0.09
    ogle
    -0.09
    è¶Ĭ
    -0.09
    andler
    -0.08
    OTAL
    -0.08
    .addAll
    -0.08
    etler
    -0.08
    _cutoff
    -0.08
     conven
    -0.08
    POSITIVE LOGITS
     alternative
    0.20
     another
    0.17
     again
    0.15
    æĸ°çļĦ
    0.14
    åı¦
    0.14
     new
    0.14
     alternatives
    0.14
    new
    0.14
     ëĭ¤ìĭľ
    0.13
    another
    0.13
    Activations Density 0.028%

    No Known Activations