© 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. 37494
    Prev
    Next
    INDEX
    Explanations

    manufacture, defence, poor economic conditions

    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
     NATO
    -0.11
     Israelis
    -0.09
     apo
    -0.09
     Mp
    -0.09
     Brill
    -0.09
     federal
    -0.09
    EGA
    -0.08
     BITS
    -0.08
    ogn
    -0.08
     Israel
    -0.08
    POSITIVE LOGITS
     surrender
    0.14
    okus
    0.12
     unconditional
    0.12
     Purple
    0.11
     OSS
    0.11
     suing
    0.11
     intercept
    0.10
     purple
    0.10
    GH
    0.10
     Lage
    0.10
    Activations Density 0.005%

    No Known Activations