© 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. 35295
    Prev
    Next
    INDEX
    Explanations

    text in parentheses

    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
     numbered
    -0.11
    ı
    -0.09
    engin
    -0.09
    642
    -0.08
     alphabetical
    -0.08
    touches
    -0.08
     ambiguous
    -0.08
     Nam
    -0.08
     palindrome
    -0.08
    ntax
    -0.08
    POSITIVE LOGITS
     paren
    0.26
    æĭ¬
    0.25
    paren
    0.22
    Paren
    0.20
     ê´
    0.20
     brackets
    0.17
     paran
    0.16
    (paren
    0.16
     Bold
    0.16
     Paren
    0.16
    Activations Density 0.344%

    No Known Activations