© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30938
    Prev
    Next
    INDEX
    Explanations

    searching and website elements

    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
     Wer
    -0.10
    ency
    -0.10
    ase
    -0.10
     cn
    -0.09
    ute
    -0.09
    _
    -0.09
     Lair
    -0.09
    yme
    -0.09
     harbour
    -0.09
     Leonard
    -0.09
    POSITIVE LOGITS
    ãģĵãĤĵãģ«
    0.11
    âĢIJâĢIJ
    0.10
    VERTISEMENT
    0.10
    ::::::::::
    0.10
    lluminate
    0.09
    egin
    0.09
    åĩºåĵģ
    0.09
    =end
    0.09
    elmet
    0.09
    :::::::::::::
    0.08
    Activations Density 0.004%

    No Known Activations