© 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. 38903
    Prev
    Next
    INDEX
    Explanations

    philosophy and thought phrases

    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
    hap
    -0.09
    oola
    -0.09
    apesh
    -0.09
     éĸ
    -0.09
     Heaven
    -0.09
    quin
    -0.08
    ãĥ¼ãĥ³
    -0.08
    abee
    -0.08
     facts
    -0.08
    toLocale
    -0.08
    POSITIVE LOGITS
    åĵ²
    0.34
     philosophy
    0.33
     philosophical
    0.32
     Philosophy
    0.29
     philosoph
    0.26
    phil
    0.25
     Philosoph
    0.24
     ÙģÙĦس
    0.23
     philosophers
    0.22
     felse
    0.21
    Activations Density 0.366%

    No Known Activations