© 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. 22027
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences and code

    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
    oyo
    -0.09
     Cary
    -0.08
     Giang
    -0.08
    clc
    -0.08
    sam
    -0.08
    еÐ
    -0.08
    odore
    -0.08
    HONE
    -0.08
     CHK
    -0.08
     queryInterface
    -0.08
    POSITIVE LOGITS
    anna
    0.08
     kola
    0.08
     aprox
    0.08
    zap
    0.08
    (parseFloat
    0.08
    ryptography
    0.08
     JpaRepository
    0.08
    ress
    0.08
    Å¡ak
    0.08
    lemetry
    0.08
    Activations Density 0.180%

    No Known Activations