© 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. 23350
    Prev
    Next
    INDEX
    Explanations

    strength of binary acids

    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
    tran
    -0.10
    inand
    -0.09
    inel
    -0.09
     succ
    -0.09
     rigid
    -0.09
    optera
    -0.08
    bate
    -0.08
    ipse
    -0.08
     Nep
    -0.08
     PropertyChanged
    -0.08
    POSITIVE LOGITS
     allot
    0.14
     dioxide
    0.12
     volatile
    0.12
    Æ¡
    0.11
     NO
    0.10
     CO
    0.10
     MO
    0.10
     RO
    0.09
     Walsh
    0.09
    é¼
    0.09
    Activations Density 0.067%

    No Known Activations