© 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. 37775
    Prev
    Next
    INDEX
    Explanations

    authenticity versus fakeness

    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
    agu
    -0.09
     stranded
    -0.08
     frankly
    -0.08
     reasonable
    -0.08
     obstruction
    -0.08
     nons
    -0.08
    iswa
    -0.08
    nila
    -0.08
     realistically
    -0.08
     Kir
    -0.08
    POSITIVE LOGITS
     authentic
    0.59
     genuine
    0.48
     Authentic
    0.47
    auth
    0.45
     authenticity
    0.43
     auth
    0.40
    Auth
    0.40
    enuine
    0.40
     Genuine
    0.36
    -auth
    0.36
    Activations Density 0.142%

    No Known Activations