© 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. 3753
    Prev
    Next
    INDEX
    Explanations

    basic phrases

    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
    èĭ±æĸĩ
    -0.13
     Lingu
    -0.11
     english
    -0.11
     slang
    -0.11
     synonyms
    -0.11
     vern
    -0.11
     shorthand
    -0.11
     lingu
    -0.10
     Vern
    -0.10
    èĭ±è¯Ń
    -0.10
    POSITIVE LOGITS
     basic
    0.20
     conjug
    0.18
    basic
    0.15
    Basic
    0.14
     Basic
    0.14
     Useful
    0.14
     useful
    0.13
     Hir
    0.13
     colors
    0.13
     numbers
    0.13
    Activations Density 0.139%

    No Known Activations