© 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. 43954
    Prev
    Next
    INDEX
    Explanations

    specific descriptive terms

    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
    ARRANT
    -0.09
     ¶
    -0.08
    ESSAGES
    -0.08
    é¡ĺãģĦ
    -0.08
    íĨłíĨł
    -0.08
     phá»iji
    -0.08
    orate
    -0.08
    krv
    -0.07
    celik
    -0.07
    rops
    -0.07
    POSITIVE LOGITS
    952
    0.08
     quot
    0.08
    0.07
    ÆĴ
    0.07
     vague
    0.07
    andro
    0.07
    arker
    0.07
    ric
    0.07
     Levi
    0.07
     Trem
    0.07
    Activations Density 0.124%

    No Known Activations