© 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. 35278
    Prev
    Next
    INDEX
    Explanations

    properties, offerings, structure, features, history

    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
    .Formatter
    -0.11
    ÂĢÂĢ
    -0.10
    ¿ÃĤ
    -0.09
    ******č\n
    -0.09
     -*-č\n
    -0.09
    ÑģÑĮ
    -0.08
    ¦æĥħ
    -0.08
    readcr
    -0.08
    ording
    -0.08
    zyst
    -0.08
    POSITIVE LOGITS
    以åıĬ
    0.09
    åıĬåħ¶
    0.09
     followed
    0.09
    ï¼Į以åıĬ
    0.09
    oa
    0.09
     Winn
    0.09
    -Origin
    0.08
     &
    0.08
    .scalablytyped
    0.08
    æ¦Ĥ
    0.08
    Activations Density 0.276%

    No Known Activations