© 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. 37660
    Prev
    Next
    INDEX
    Explanations

    experimentation

    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
    iny
    -0.10
     Butler
    -0.09
     reconsider
    -0.08
     Challenger
    -0.08
    StringLength
    -0.08
     Indices
    -0.08
     Tiffany
    -0.08
    ayi
    -0.08
    490
    -0.08
     hardest
    -0.08
    POSITIVE LOGITS
     trial
    0.33
     Trial
    0.25
    trial
    0.24
    Trial
    0.23
     experiment
    0.22
     trials
    0.22
    Experiment
    0.21
     testing
    0.20
    experiment
    0.20
     Experiment
    0.19
    Activations Density 0.058%

    No Known Activations