© 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. 45420
    Prev
    Next
    INDEX
    Explanations

    underscore character

    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
     ï½²
    -0.13
    âĢķâĢķâĢķâĢķ
    -0.11
     brackets
    -0.10
     sal
    -0.09
    ạc
    -0.09
     unidentified
    -0.09
    uppercase
    -0.09
    ç¯
    -0.08
    rotch
    -0.08
     comma
    -0.08
    POSITIVE LOGITS
     hy
    0.24
    underscore
    0.23
     underscores
    0.20
     underscore
    0.20
     Und
    0.19
    unders
    0.19
     dash
    0.19
    Und
    0.18
     Dash
    0.17
     Hy
    0.17
    Activations Density 0.097%

    No Known Activations