© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 57326
    Prev
    Next
    INDEX
    Explanations

    in other words

    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
     Gloss
    -0.10
    azu
    -0.09
     abbreviation
    -0.09
     slang
    -0.09
     acronym
    -0.09
     gloss
    -0.09
     derog
    -0.09
    494
    -0.09
    227
    -0.08
    ingu
    -0.08
    POSITIVE LOGITS
     words
    0.72
    words
    0.52
     Words
    0.49
    Words
    0.45
     palabras
    0.44
     Ñģлова
    0.40
    _words
    0.40
    .words
    0.37
    WORDS
    0.37
    (words
    0.36
    Activations Density 0.210%

    No Known Activations