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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38652
    Prev
    Next
    INDEX
    Explanations

    opportunities and challenges

    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
     impro
    -0.12
    æĿī
    -0.09
    lassen
    -0.09
     chilling
    -0.09
    loh
    -0.09
    zim
    -0.09
     Rosenberg
    -0.09
     Impro
    -0.09
    å¦
    -0.08
    Impro
    -0.08
    POSITIVE LOGITS
     opportunities
    0.22
     opportunity
    0.20
     changes
    0.19
     Opportunities
    0.18
     challenge
    0.18
     challenges
    0.18
     change
    0.17
     oportun
    0.16
     changed
    0.16
    æĸ°çļĦ
    0.16
    Activations Density 0.110%

    No Known Activations