© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44132
    Prev
    Next
    INDEX
    Explanations

    depends on capacity

    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
    -is
    -0.10
    ä¹Ī
    -0.09
    åIJ§
    -0.09
    åIJĹ
    -0.09
     nhé
    -0.09
    tered
    -0.09
    alt
    -0.08
    rai
    -0.08
    949
    -0.08
    ffi
    -0.08
    POSITIVE LOGITS
     depends
    0.24
    depends
    0.18
     завиÑģиÑĤ
    0.17
     depend
    0.16
     Depends
    0.15
     depended
    0.12
    ìĤ¬ëĬĶ
    0.11
    sis
    0.11
    ì§ĢëĬĶ
    0.11
     remains
    0.11
    Activations Density 0.225%

    No Known Activations