© 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. 27505
    Prev
    Next
    INDEX
    Explanations

    many parallel threads

    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
    -0.14
     IReadOnly
    -0.13
     DataColumn
    -0.11
     SelectList
    -0.10
     Py
    -0.10
     functionName
    -0.10
    >Returns
    -0.10
     MSP
    -0.09
    dsp
    -0.09
     functions
    -0.09
    POSITIVE LOGITS
    .cs
    0.18
    GuidId
    0.17
     foreach
    0.16
    .IsNullOr
    0.14
    BackingField
    0.14
     EF
    0.13
    EF
    0.13
    foreach
    0.13
    .NET
    0.13
     Uri
    0.13
    Activations Density 0.140%

    No Known Activations