© 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. 33815
    Prev
    Next
    INDEX
    Explanations

    sense and feeling

    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
    ＿__
    -0.10
    mdb
    -0.10
    snd
    -0.09
     NavParams
    -0.09
    .WinForms
    -0.08
     Gener
    -0.08
    Href
    -0.08
    FINE
    -0.08
    unas
    -0.08
    ãĥ¼ãĥ«
    -0.08
    POSITIVE LOGITS
     sense
    0.94
     Sense
    0.75
    sense
    0.70
    Sense
    0.67
     sentido
    0.53
     feeling
    0.49
    ense
    0.37
     Feeling
    0.33
     scn
    0.33
    ENSE
    0.33
    Activations Density 0.082%

    No Known Activations