© 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. 41181
    Prev
    Next
    INDEX
    Explanations

    distributed systems and computing

    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
     Cald
    -0.12
    ium
    -0.10
    odel
    -0.10
     flawed
    -0.09
     Nob
    -0.09
     Division
    -0.08
    ."&
    -0.08
     Benton
    -0.08
    baum
    -0.08
    adm
    -0.08
    POSITIVE LOGITS
    å¼ı
    0.14
     nature
    0.12
     ledger
    0.12
     systems
    0.12
    /shared
    0.11
     computing
    0.11
    uteur
    0.10
     fashion
    0.10
     Ledger
    0.10
    .scalablytyped
    0.10
    Activations Density 0.015%

    No Known Activations