© 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. 30285
    Prev
    Next
    INDEX
    Explanations

    generate random data

    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
    輪
    -0.10
     Rings
    -0.10
    alphabet
    -0.10
    è½®
    -0.09
     Numer
    -0.09
     Starr
    -0.09
     Char
    -0.09
    Alternate
    -0.09
     Numeric
    -0.09
     Prompt
    -0.09
    POSITIVE LOGITS
     random
    0.31
    .random
    0.24
    éļı
    0.23
    random
    0.22
     Random
    0.20
     ÑģлÑĥÑĩай
    0.19
    \trandom
    0.19
    Random
    0.18
    éļ¨
    0.18
    -random
    0.18
    Activations Density 0.059%

    No Known Activations