© 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. 29499
    Prev
    Next
    INDEX
    Explanations

    Xian smart contract honor someone

    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
    ¶Į
    -0.12
    ******č\n
    -0.11
    įng
    -0.09
     CascadeType
    -0.08
    .Formatter
    -0.08
    <|begin_of_text|>
    -0.08
     GenerationType
    -0.08
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    -0.08
    ³Øª
    -0.08
    ħn
    -0.08
    POSITIVE LOGITS
     UNICODE
    0.08
    (NAME
    0.07
    DataRow
    0.07
    XMLElement
    0.07
    911
    0.07
    pedia
    0.06
    AppDelegate
    0.06
    âĢ¦âĢ¦ãĢĤ
    0.06
     âĸ²
    0.06
    erialized
    0.06
    Activations Density 0.197%

    No Known Activations