© 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. 53688
    Prev
    Next
    INDEX
    Explanations

    Glados, Decadent-, Charming, Sokrates

    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
    utral
    -0.09
    ikon
    -0.09
     RAF
    -0.08
     Twig
    -0.08
    angkan
    -0.08
     Sta
    -0.08
    çon
    -0.08
    æ³Ľ
    -0.08
     clandest
    -0.08
    re
    -0.08
    POSITIVE LOGITS
    rael
    0.14
    -chan
    0.11
    adius
    0.11
    odore
    0.11
    etheus
    0.10
    icles
    0.10
    etooth
    0.10
    ãģ£ãģ¡
    0.09
    ]][
    0.09
    ÄŁmen
    0.09
    Activations Density 0.245%

    No Known Activations