© 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. 42922
    Prev
    Next
    INDEX
    Explanations

    sequences after punctuation

    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
    Lastly
    -0.11
     Lastly
    -0.10
     third
    -0.09
     Brig
    -0.09
    ãģķãģĦ
    -0.08
     finally
    -0.08
    <dd
    -0.08
    zee
    -0.08
    urn
    -0.08
     Loves
    -0.08
    POSITIVE LOGITS
     Another
    0.11
     another
    0.11
     Second
    0.11
     second
    0.11
    Similarly
    0.11
     Similarly
    0.11
    âij¡
    0.10
     br
    0.10
     Next
    0.10
     SECOND
    0.10
    Activations Density 0.114%

    No Known Activations