© 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. 10353
    Prev
    Next
    INDEX
    Explanations

    name placeholders

    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
     ëĦ¤ìĿ´íĬ¸
    -0.09
    oose
    -0.09
    /WebAPI
    -0.08
    ichert
    -0.08
     porr
    -0.08
     Dorothy
    -0.08
    alien
    -0.08
     geil
    -0.08
    occo
    -0.08
     klu
    -0.08
    POSITIVE LOGITS
     space
    0.10
    opi
    0.10
    à¹Ĩ
    0.09
    space
    0.09
     ward
    0.09
    âĢ³
    0.09
     wards
    0.09
     SPACE
    0.08
     Singer
    0.08
     Rout
    0.08
    Activations Density 0.063%

    No Known Activations