© 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. 722
    Prev
    Next
    INDEX
    Explanations

    rules for sentences

    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
     vowels
    -0.11
     words
    -0.11
    è¯į
    -0.11
    åŃĹ
    -0.10
     lexical
    -0.10
     Words
    -0.10
    usra
    -0.10
    uchos
    -0.09
    Words
    -0.09
    uby
    -0.09
    POSITIVE LOGITS
     sentence
    0.25
     sentences
    0.21
     Sentence
    0.18
    sentence
    0.18
    åı¥
    0.17
     sentenced
    0.16
    Sentence
    0.14
    (sentence
    0.14
     declar
    0.14
     Sent
    0.14
    Activations Density 0.326%

    No Known Activations