© 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. 59636
    Prev
    Next
    INDEX
    Explanations

    emotion and sentiment detection

    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
     Imperial
    -0.10
     Eleanor
    -0.09
    à¸Ļว
    -0.09
     ears
    -0.09
    omm
    -0.09
    APO
    -0.08
     Ein
    -0.08
     hypnot
    -0.08
    º¼
    -0.08
    daÅŁ
    -0.08
    POSITIVE LOGITS
     emotions
    0.54
     emotion
    0.51
    æĥħ
    0.37
     emoc
    0.36
     emotional
    0.36
     Em
    0.36
    çļĦæĥħ
    0.35
    æĦŁæĥħ
    0.34
    emotion
    0.33
     emo
    0.32
    Activations Density 0.237%

    No Known Activations