© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 35293
    Prev
    Next
    INDEX
    Explanations

    decode, decompress, parse, undo

    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
    encrypt
    -0.14
     encrypt
    -0.14
    _encrypt
    -0.13
     Encrypt
    -0.13
    .encrypt
    -0.12
    Encrypt
    -0.12
    .SerializeObject
    -0.11
    .compress
    -0.11
    .serialize
    -0.10
    .Escape
    -0.10
    POSITIVE LOGITS
    è§£
    0.24
     decode
    0.20
     è§£
    0.19
     inverse
    0.19
     reverse
    0.19
     undo
    0.18
     Dec
    0.18
     decoding
    0.17
    decode
    0.17
    undo
    0.17
    Activations Density 0.081%

    No Known Activations