© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    articles and nouns

    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
     ï½°
    -0.10
     Verfüg
    -0.08
    inging
    -0.08
    nger
    -0.08
     dint
    -0.08
    zier
    -0.08
    ynes
    -0.08
    _MAJOR
    -0.08
    ĥn
    -0.08
     bacheca
    -0.08
    POSITIVE LOGITS
     same
    0.15
     Same
    0.11
    Same
    0.11
    same
    0.10
     said
    0.10
    該
    0.10
     SAME
    0.10
    该
    0.10
     íķ´ëĭ¹
    0.09
    åIJĮ
    0.09
    Activations Density 0.114%

    No Known Activations