© 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. 30436
    Prev
    Next
    INDEX
    Explanations

    "The Impact" or "Application" phrases

    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
     secular
    -0.09
    rael
    -0.09
     Modal
    -0.09
    çIJ
    -0.09
     modal
    -0.09
     Spice
    -0.09
     feeder
    -0.09
    .mov
    -0.09
     Fiscal
    -0.09
     sanct
    -0.09
    POSITIVE LOGITS
     firm
    0.16
     firms
    0.14
    firm
    0.14
     Barney
    0.13
     Firm
    0.12
     literature
    0.12
     DEA
    0.12
     slack
    0.12
     XB
    0.12
     Supply
    0.11
    Activations Density 0.100%

    No Known Activations