© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56877
    Prev
    Next
    INDEX
    Explanations

    devops and development related terms

    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
    ench
    -0.10
    oft
    -0.10
    entic
    -0.10
    enal
    -0.09
    is
    -0.09
    asin
    -0.09
    chalk
    -0.09
    ibia
    -0.09
    alam
    -0.09
    ERM
    -0.09
    POSITIVE LOGITS
    lop
    0.18
    /null
    0.16
    ils
    0.16
    olution
    0.15
    olve
    0.15
    implify
    0.15
    Ops
    0.15
    oted
    0.14
     dev
    0.14
    elopment
    0.14
    Activations Density 0.023%

    No Known Activations