© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35239
    Prev
    Next
    INDEX
    Explanations

    organizational aspects or components

    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
    ãĢģä¸Ģ
    -0.10
    pong
    -0.09
    hle
    -0.09
    iele
    -0.09
    ovsky
    -0.09
     Borg
    -0.09
     manned
    -0.08
    643
    -0.08
    aller
    -0.08
     Gupta
    -0.08
    POSITIVE LOGITS
     gal
    0.19
     apl
    0.14
    plural
    0.13
    .scalablytyped
    0.12
     gì
    0.11
    гал
    0.11
    -ÑĤо
    0.11
     GAL
    0.11
     Gal
    0.11
    yb
    0.10
    Activations Density 0.254%

    No Known Activations