© 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. 27141
    Prev
    Next
    INDEX
    Explanations

    when providing support or guidance

    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
     Pav
    -0.09
    kah
    -0.08
    Č\n
    -0.08
    vd
    -0.08
    abbo
    -0.08
    ì§ľ
    -0.08
     aldı
    -0.07
    ê°ĢìļĶ
    -0.07
     Apprec
    -0.07
    467
    -0.07
    POSITIVE LOGITS
     when
    0.55
    when
    0.47
     whenever
    0.45
     quando
    0.41
     когда
    0.39
     khi
    0.38
     cuando
    0.38
     WHEN
    0.36
     när
    0.35
     When
    0.33
    Activations Density 0.128%

    No Known Activations