© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 54501
    Prev
    Next
    INDEX
    Explanations

    in fact, indeed

    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
    itti
    -0.09
    /do
    -0.09
     Bau
    -0.08
    ализи
    -0.08
    itty
    -0.08
    âĢª
    -0.08
    çĦ¡ãģĹãģ
    -0.08
    dex
    -0.08
    สมà¸ļ
    -0.08
     bl
    -0.08
    POSITIVE LOGITS
     indeed
    0.29
     fact
    0.25
     Indeed
    0.20
    fact
    0.19
    Indeed
    0.19
     truth
    0.19
     fakt
    0.17
     actually
    0.16
     Fact
    0.16
    Fact
    0.16
    Activations Density 0.057%

    No Known Activations