© 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. 49024
    Prev
    Next
    INDEX
    Explanations

    may occur

    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
    765
    -0.09
     Futures
    -0.08
    kl
    -0.08
    _frag
    -0.08
    acci
    -0.08
    iani
    -0.08
    ola
    -0.08
     invariably
    -0.08
    lass
    -0.08
    andan
    -0.08
    POSITIVE LOGITS
     often
    0.45
    often
    0.33
     Often
    0.32
     souvent
    0.31
     ÑĩаÑģÑĤо
    0.30
    Often
    0.28
     Äįasto
    0.27
     thÆ°á»Ŀng
    0.27
    å¾Ģ
    0.26
     frequently
    0.26
    Activations Density 0.169%

    No Known Activations