© 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. 33620
    Prev
    Next
    INDEX
    Explanations

    feelings and emotions

    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
    íĴį
    -0.09
    373
    -0.09
    Else
    -0.09
    expo
    -0.09
    apo
    -0.09
    ordan
    -0.08
     ellipt
    -0.08
     crowned
    -0.08
    invitation
    -0.08
     becoming
    -0.08
    POSITIVE LOGITS
     about
    0.14
     AF
    0.11
    hoa
    0.10
    tring
    0.10
     Closure
    0.09
    UIL
    0.09
     tentang
    0.09
     Wel
    0.09
    about
    0.09
    tc
    0.09
    Activations Density 0.054%

    No Known Activations