© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 489
    Prev
    Next
    INDEX
    Explanations

    repeatable deployments and provisioning

    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
    ernel
    -0.11
    kas
    -0.09
    /AFP
    -0.09
     ÐĴики
    -0.09
     ux
    -0.09
    _endian
    -0.09
     ï¼ı
    -0.09
     vista
    -0.09
    cone
    -0.09
     SAS
    -0.09
    POSITIVE LOGITS
     repro
    0.16
     provision
    0.15
     declar
    0.13
     Terra
    0.13
     Desired
    0.12
     repeat
    0.12
     terra
    0.12
     infrastructure
    0.12
     Spin
    0.12
    ulumi
    0.12
    Activations Density 0.089%

    No Known Activations