© 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. 61940
    Prev
    Next
    INDEX
    Explanations

    specific concepts and states

    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
    лиÑĪком
    -0.08
     Rencontres
    -0.08
    lider
    -0.08
     destinationViewController
    -0.07
    ¶Į
    -0.07
    ypad
    -0.07
    innen
    -0.07
    ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ ãĢĢ
    -0.07
    returnValue
    -0.07
    bfd
    -0.07
    POSITIVE LOGITS
     towards
    0.11
     toward
    0.10
     Abrams
    0.09
    ómo
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.08
     %[
    0.08
    /of
    0.08
     yani
    0.08
     regarding
    0.08
    lessly
    0.08
    Activations Density 0.180%

    No Known Activations