© 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. 38825
    Prev
    Next
    INDEX
    Explanations

    expressions of love

    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
    lo
    -0.12
     loving
    -0.12
    so
    -0.11
    ss
    -0.11
    ness
    -0.10
    abra
    -0.10
    man
    -0.10
    ura
    -0.10
    -loving
    -0.10
     Verse
    -0.10
    POSITIVE LOGITS
     affair
    0.18
     affairs
    0.17
    able
    0.17
    craft
    0.17
    birds
    0.16
    joy
    0.16
     Potion
    0.14
     triangle
    0.14
    leen
    0.13
    bug
    0.13
    Activations Density 0.025%

    No Known Activations