© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 39243
    Prev
    Next
    INDEX
    Explanations

    not at the moment

    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
    ëij¥
    -0.10
     glad
    -0.09
    ãĥĨãĥ«
    -0.09
    imo
    -0.09
     Glad
    -0.09
    stringValue
    -0.08
    Fizz
    -0.08
    Granted
    -0.08
     obviously
    -0.08
     Guil
    -0.08
    POSITIVE LOGITS
     thanks
    0.21
     thank
    0.21
     Thanks
    0.18
    Thanks
    0.17
     everything
    0.16
     Thank
    0.16
     THANK
    0.16
    thanks
    0.15
     thanked
    0.15
    Thank
    0.15
    Activations Density 0.036%

    No Known Activations