© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21892
    Prev
    Next
    INDEX
    Explanations

    used, his, every, distracted, managed, I'm, my, took, lose, were, feel

    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
    staking
    -0.10
    emann
    -0.09
    Qualifier
    -0.09
    icios
    -0.09
    _FIXED
    -0.09
    .disabled
    -0.09
    lator
    -0.09
    ::::|
    -0.09
    phan
    -0.08
    ValueChanged
    -0.08
    POSITIVE LOGITS
     bot
    0.24
     fail
    0.22
     struggle
    0.21
     fails
    0.19
     fal
    0.18
     failed
    0.17
     FAIL
    0.16
    bot
    0.16
     struggles
    0.16
     Bot
    0.16
    Activations Density 0.153%

    No Known Activations