© 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. 60811
    Prev
    Next
    INDEX
    Explanations

    Bronfenbrenner's ecological systems

    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
     stub
    -0.10
    .scalablytyped
    -0.10
    Intialized
    -0.09
     Soft
    -0.09
    getError
    -0.09
     Cad
    -0.09
    kad
    -0.08
     Mori
    -0.08
    UrlParser
    -0.08
     Harm
    -0.08
    POSITIVE LOGITS
     Pi
    0.28
    Pi
    0.24
     Erik
    0.21
     Koh
    0.20
     development
    0.18
     Development
    0.18
     pi
    0.18
     Stage
    0.16
     stage
    0.16
    Development
    0.16
    Activations Density 0.042%

    No Known Activations