© 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. 16734
    Prev
    Next
    INDEX
    Explanations

    peace of mind

    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
     Schro
    -0.10
     Tk
    -0.09
    ucu
    -0.09
    uga
    -0.08
    887
    -0.08
    무
    -0.08
     nors
    -0.08
     opport
    -0.08
    .Sprintf
    -0.08
    radu
    -0.08
    POSITIVE LOGITS
     confidence
    0.36
     knowing
    0.34
    confidence
    0.29
     confident
    0.29
     peace
    0.28
     Confidence
    0.27
    -confidence
    0.24
     rest
    0.23
     Knowing
    0.23
     ÑĥвеÑĢ
    0.22
    Activations Density 0.052%

    No Known Activations