© 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. 16419
    Prev
    Next
    INDEX
    Explanations

    each or every

    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
     Andres
    -0.12
     yearly
    -0.11
     annual
    -0.10
     Annual
    -0.10
    APPER
    -0.09
    loo
    -0.09
    Annual
    -0.09
     ï½ī
    -0.09
    ymm
    -0.09
    olla
    -0.09
    POSITIVE LOGITS
     each
    0.29
     ap
    0.28
    ìĶ©
    0.27
    each
    0.23
     EACH
    0.22
    ãģļ
    0.21
     chac
    0.21
     cada
    0.20
     per
    0.19
    _each
    0.18
    Activations Density 0.179%

    No Known Activations