© 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. 23144
    Prev
    Next
    INDEX
    Explanations

    significance and meaning

    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
    ometric
    -0.09
    ichel
    -0.09
    returnValue
    -0.09
    ewise
    -0.09
    CID
    -0.08
    302
    -0.08
    ＿＿
    -0.08
     Brennan
    -0.08
    orest
    -0.08
    atak
    -0.08
    POSITIVE LOGITS
     significance
    0.47
     signific
    0.35
    æĦıä¹ī
    0.34
     meaningful
    0.31
     meaning
    0.31
     significant
    0.28
     importance
    0.27
     special
    0.27
    meaning
    0.27
     Meaning
    0.26
    Activations Density 0.197%

    No Known Activations