© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 59257
    Prev
    Next
    INDEX
    Explanations

    use many rare or offensive words

    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
     vowels
    -0.10
     pronunciation
    -0.10
     inscription
    -0.09
    ç´ł
    -0.09
    æĸĩåŃĹ
    -0.09
    _VERBOSE
    -0.09
    istring
    -0.09
     fug
    -0.09
     captions
    -0.09
    ÑĤов
    -0.09
    POSITIVE LOGITS
     ell
    0.14
     regional
    0.13
     analog
    0.12
     pun
    0.12
     emot
    0.11
     terms
    0.11
     dimin
    0.11
     imper
    0.11
     ac
    0.11
     nets
    0.10
    Activations Density 0.135%

    No Known Activations