© 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. 33745
    Prev
    Next
    INDEX
    Explanations

    destination or goal

    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
    itional
    -0.09
    pty
    -0.09
     ongoing
    -0.08
    inton
    -0.08
    ongo
    -0.08
     tallest
    -0.08
    ymous
    -0.08
     breeze
    -0.08
     thwart
    -0.08
     Suche
    -0.08
    POSITIVE LOGITS
     conclusion
    0.26
     destination
    0.25
     conclusions
    0.22
     goal
    0.20
     destinations
    0.19
     solution
    0.18
     Destination
    0.17
     outcome
    0.17
    Conclusion
    0.17
    destination
    0.17
    Activations Density 0.103%

    No Known Activations