© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 45147
    Prev
    Next
    INDEX
    Explanations

    astrology and tarot

    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
     Maid
    -0.09
     PTR
    -0.08
     Foley
    -0.08
     Alv
    -0.08
    ãĤīãģĦ
    -0.08
     Oral
    -0.08
    ement
    -0.08
     Holt
    -0.08
     tsl
    -0.08
    leck
    -0.08
    POSITIVE LOGITS
     hor
    0.36
     Hor
    0.24
    Hor
    0.21
    hor
    0.20
    astro
    0.20
     tar
    0.20
     birth
    0.19
     transit
    0.18
     chart
    0.18
     numer
    0.17
    Activations Density 0.058%

    No Known Activations