© 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. 34975
    Prev
    Next
    INDEX
    Explanations

    azzurro

    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
     Weston
    -0.09
    ï½ŀï½ŀ
    -0.08
     Charg
    -0.08
     Alic
    -0.08
     mojo
    -0.08
     Bale
    -0.08
     frauen
    -0.08
    ">//
    -0.08
     mark
    -0.08
     Cookie
    -0.07
    POSITIVE LOGITS
    ,\n
    0.13
    ,/
    0.09
    женÑĮ
    0.09
     ÑĢанÑĮ
    0.09
    анÑĮ
    0.08
     Hanson
    0.08
     Farrell
    0.08
    
    0.08
     ÑģÑĢок
    0.08
    umbs
    0.08
    Activations Density 0.150%

    No Known Activations