© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58294
    Prev
    Next
    INDEX
    Explanations

    truthfulness and deception

    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
     dem
    -0.10
     hearing
    -0.10
     Shir
    -0.09
     Survey
    -0.09
     ARGS
    -0.09
     tun
    -0.09
     QR
    -0.09
    Hints
    -0.09
    geh
    -0.09
     Gad
    -0.09
    POSITIVE LOGITS
     lie
    0.23
     poly
    0.21
     Lie
    0.16
    lying
    0.16
    lie
    0.15
     Poly
    0.15
     lying
    0.15
    Lie
    0.15
    poly
    0.14
     liar
    0.13
    Activations Density 0.032%

    No Known Activations