© 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. 35138
    Prev
    Next
    INDEX
    Explanations

    case conversion lower upper

    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
    .Ordinal
    -0.13
     comma
    -0.10
    åĨ
    -0.10
    strncmp
    -0.09
    strstr
    -0.09
    LAG
    -0.09
     Caldwell
    -0.09
    æ»
    -0.09
    canf
    -0.09
    oram
    -0.09
    POSITIVE LOGITS
     case
    0.31
     lower
    0.30
     Case
    0.27
    Case
    0.27
    case
    0.26
     Lower
    0.25
    lower
    0.25
    -case
    0.24
     upper
    0.23
    _case
    0.23
    Activations Density 0.080%

    No Known Activations