© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11404
    Prev
    Next
    INDEX
    Explanations

    use a web framework

    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
    Negative Logits
    _cmos
    -0.10
     Semaphore
    -0.10
    .Transactional
    -0.10
    StringEncoding
    -0.09
    RuntimeObject
    -0.09
     feeding
    -0.09
    GenerationStrategy
    -0.09
    FilterWhere
    -0.09
    ocache
    -0.09
     HDMI
    -0.09
    POSITIVE LOGITS
     listening
    0.16
     Transport
    0.15
     Net
    0.15
     Listening
    0.15
     transport
    0.15
     socket
    0.14
     listen
    0.14
     Establish
    0.14
     Listen
    0.14
     client
    0.14
    Activations Density 0.178%

    No Known Activations