© 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. 54948
    Prev
    Next
    INDEX
    Explanations

    while structure

    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
     indeed
    -0.12
    ãģ§ãģ¯ãģªãģı
    -0.10
    inde
    -0.09
    trinsic
    -0.09
    PFN
    -0.09
     totiž
    -0.09
     opposed
    -0.09
    çĦ¶åIJİ
    -0.09
    uzey
    -0.09
    xBD
    -0.08
    POSITIVE LOGITS
    åīĩ
    0.20
    åĪĻ
    0.19
     more
    0.16
     convers
    0.16
     naopak
    0.16
     ê·¸ëłĩ
    0.16
    æĽ´åĬł
    0.13
     counterpart
    0.12
     zase
    0.12
     counterparts
    0.12
    Activations Density 0.076%

    No Known Activations