© 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. 35672
    Prev
    Next
    INDEX
    Explanations

    crucial 're absolutely or scenario by

    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
     overturn
    -0.09
    ť
    -0.09
    eya
    -0.09
     Handy
    -0.08
    \tfreopen
    -0.08
    WARN
    -0.08
    ese
    -0.08
    ekk
    -0.08
    allback
    -0.08
     Interr
    -0.08
    POSITIVE LOGITS
     crucial
    0.15
     trick
    0.15
     importantly
    0.13
    åħ³éĶ®
    0.13
     enter
    0.12
     here
    0.11
     key
    0.11
     Enter
    0.11
     now
    0.11
     Notice
    0.11
    Activations Density 0.088%

    No Known Activations