© 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. 16554
    Prev
    Next
    INDEX
    Explanations

    typically followed by description

    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
     sometimes
    -0.12
    åĩłä¹İ
    -0.11
     olabilir
    -0.11
     possibly
    -0.10
     duly
    -0.10
     skoro
    -0.09
    almost
    -0.09
    लà¤Ĺ
    -0.09
     almost
    -0.09
    sometimes
    -0.09
    POSITIVE LOGITS
     either
    0.23
    either
    0.17
     somewhere
    0.15
     Either
    0.14
     EITHER
    0.14
    Either
    0.13
     rather
    0.13
     fairly
    0.13
     irgend
    0.12
     qualche
    0.11
    Activations Density 0.220%

    No Known Activations