© 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. 28596
    Prev
    Next
    INDEX
    Explanations

    MS followed by various initials

    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
    oftware
    -0.13
    h
    -0.12
    sville
    -0.10
    TL
    -0.10
     cave
    -0.10
    ETF
    -0.10
    et
    -0.09
    .Parse
    -0.09
     Cave
    -0.09
    t
    -0.09
    POSITIVE LOGITS
    /ms
    0.17
     MS
    0.15
     ms
    0.13
    FT
    0.12
    NBC
    0.12
    MS
    0.11
    (ms
    0.11
    ieur
    0.10
     Paint
    0.10
     Word
    0.10
    Activations Density 0.028%

    No Known Activations