© 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. 39247
    Prev
    Next
    INDEX
    Explanations

    say anything

    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
     bye
    -0.11
     Bye
    -0.10
    PrimaryKey
    -0.09
    ÛĮÙĩ
    -0.09
     Baum
    -0.09
    ended
    -0.09
     situ
    -0.09
    erne
    -0.08
    zel
    -0.08
    pts
    -0.08
    POSITIVE LOGITS
     anything
    0.15
    anything
    0.14
     things
    0.13
    æľį
    0.13
     words
    0.12
    ings
    0.12
     something
    0.12
     uncle
    0.11
    /do
    0.11
     sorry
    0.10
    Activations Density 0.047%

    No Known Activations