© 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. 25145
    Prev
    Next
    INDEX
    Explanations

    matrix entries and diagonals

    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
     sext
    -0.11
     Johann
    -0.10
    ewan
    -0.09
     Sext
    -0.09
     Junction
    -0.09
     Meer
    -0.09
     Pol
    -0.09
    çIJ´
    -0.09
     multiply
    -0.08
     Westbrook
    -0.08
    POSITIVE LOGITS
     entries
    0.30
    entries
    0.26
     Entries
    0.24
     entry
    0.23
    Entries
    0.22
    entry
    0.20
    _entries
    0.20
     Entry
    0.18
     diagonal
    0.17
    Entry
    0.17
    Activations Density 0.051%

    No Known Activations