© 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. 927
    Prev
    Next
    INDEX
    Explanations

    achieving a greater good

    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
     usage
    -0.09
     rival
    -0.09
     Intercept
    -0.09
    ä¹Ļ
    -0.08
     scour
    -0.08
    èĪį
    -0.08
     gut
    -0.08
     Ler
    -0.08
     interle
    -0.08
     conspir
    -0.08
    POSITIVE LOGITS
     expression
    0.17
     communication
    0.15
     escape
    0.13
    expression
    0.13
    communication
    0.13
    -expression
    0.12
     escap
    0.12
     survival
    0.12
     Communication
    0.12
    Communication
    0.12
    Activations Density 0.081%

    No Known Activations