© 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. 17759
    Prev
    Next
    INDEX
    Explanations

    noise cancellation performances

    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
    Illuminate
    -0.11
    .lua
    -0.09
    æĿ
    -0.09
     agon
    -0.08
    zza
    -0.08
     sequ
    -0.08
    anim
    -0.08
     failures
    -0.08
    FAIL
    -0.08
     prog
    -0.08
    POSITIVE LOGITS
     cancellation
    0.19
     noise
    0.18
     Noise
    0.17
     cancel
    0.17
    Cancellation
    0.16
     cancelling
    0.16
     Cancel
    0.15
    noise
    0.14
    Noise
    0.14
     ac
    0.14
    Activations Density 0.023%

    No Known Activations