© 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. 703
    Prev
    Next
    INDEX
    Explanations

    tell stories or lies

    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
     Sachs
    -0.10
    ienda
    -0.10
    ool
    -0.10
    zel
    -0.10
    ican
    -0.09
     )\n\n\n\n\n\n\n\n
    -0.09
     Anc
    -0.09
    841
    -0.09
    CESS
    -0.09
    zu
    -0.09
    POSITIVE LOGITS
     fortunes
    0.19
    ingly
    0.16
     lies
    0.15
     jokes
    0.15
     apart
    0.15
     us
    0.14
     fib
    0.14
     stories
    0.13
    Apart
    0.13
    IGENCE
    0.12
    Activations Density 0.036%

    No Known Activations