© 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. 36260
    Prev
    Next
    INDEX
    Explanations

    bank channel effectiveness

    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
     IIC
    -0.09
     å·Ŀ
    -0.09
     Hatch
    -0.09
     Sor
    -0.09
     tissue
    -0.09
     quot
    -0.09
     compar
    -0.09
     col
    -0.08
    lov
    -0.08
     Hedge
    -0.08
    POSITIVE LOGITS
     multiplier
    0.16
     Hicks
    0.14
     Aggregate
    0.13
     Mund
    0.13
     demand
    0.13
     AD
    0.13
     unemployment
    0.13
     goods
    0.12
     mac
    0.12
    å®ı
    0.12
    Activations Density 0.026%

    No Known Activations