© 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. 35385
    Prev
    Next
    INDEX
    Explanations

    column/values conditional filling

    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
     Parameters
    -0.09
     Bernstein
    -0.09
    Parameters
    -0.09
    ç¼ĸåı·
    -0.09
    vod
    -0.09
    .openg
    -0.09
    hart
    -0.09
     parameters
    -0.08
     requested
    -0.08
     nome
    -0.08
    POSITIVE LOGITS
     values
    0.27
    values
    0.22
     column
    0.21
     Values
    0.20
    Values
    0.17
     entries
    0.17
    _values
    0.17
     field
    0.17
    -values
    0.16
     valores
    0.16
    Activations Density 0.130%

    No Known Activations