© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32834
    Prev
    Next
    INDEX
    Explanations

    fairytale princess proclamation and lounging

    np_acts-logits-general · gemini-2.5-flash-lite

    narrative storytelling language, particularly fairy tale or storybook-style phrases.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     doll
    -0.11
     Doll
    -0.11
     devil
    -0.10
     dol
    -0.09
     Dol
    -0.09
    鬼
    -0.09
     shark
    -0.09
    doch
    -0.09
     dolls
    -0.09
    ismic
    -0.09
    POSITIVE LOGITS
     Frog
    0.15
     frogs
    0.15
    frog
    0.14
     frog
    0.14
    pond
    0.13
     prince
    0.13
     amphib
    0.12
     pond
    0.12
     Pond
    0.12
     Prince
    0.11
    Activations Density 0.033%

    No Known Activations