© 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. 23899
    Prev
    Next
    INDEX
    Explanations

    lists phrases starting with comma-separated clauses

    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
    .API
    -0.09
    957
    -0.09
    yntax
    -0.08
    nap
    -0.08
    äter
    -0.08
    éĿł
    -0.08
    owitz
    -0.08
    uo
    -0.08
     Goodman
    -0.08
    ayload
    -0.08
    POSITIVE LOGITS
    enas
    0.09
    以åıĬ
    0.09
    --+
    0.09
     starting
    0.09
    ãģĬãĤĪãģ³
    0.09
    éĴĪ
    0.09
    agn
    0.08
     ÙĪØ°ÙĦÙĥ
    0.08
    989
    0.08
    arlo
    0.08
    Activations Density 0.168%

    No Known Activations