© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 13109
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks

    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
    asyarak
    -0.10
    ¶Į
    -0.10
    issional
    -0.09
    <|begin_of_text|>
    -0.09
    ******č\n
    -0.09
    įng
    -0.08
     teng
    -0.08
    EMPLARY
    -0.08
    lick
    -0.08
     ëķĮ문
    -0.08
    POSITIVE LOGITS
     thank
    0.15
     Thank
    0.13
     thanks
    0.12
    thank
    0.12
    Thank
    0.11
     Thanks
    0.10
    thanks
    0.10
     OP
    0.10
    è°¢
    0.09
     THANK
    0.09
    Activations Density 0.088%

    No Known Activations