© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39135
    Prev
    Next
    INDEX
    Explanations

    mutual respect and praise

    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
     loved
    -0.11
     Loved
    -0.11
     beloved
    -0.10
    atar
    -0.10
     pending
    -0.10
    ynam
    -0.10
     Fitzgerald
    -0.09
     equ
    -0.09
     skeletons
    -0.09
     seemingly
    -0.09
    POSITIVE LOGITS
     mutual
    0.17
    adm
    0.14
     cord
    0.14
    äºĴ
    0.12
     respect
    0.12
     Mutual
    0.12
    mut
    0.11
     colleg
    0.11
     friendly
    0.11
     respects
    0.11
    Activations Density 0.055%

    No Known Activations