© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53356
    Prev
    Next
    INDEX
    Explanations

    Hello there, to me, a vector

    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
    Negative Logits
    .Hex
    -0.10
    reau
    -0.09
     breakdown
    -0.09
    ì¶Ķ
    -0.08
    _Framework
    -0.08
     contest
    -0.08
     ÐĴлади
    -0.08
    inya
    -0.08
    æ¡IJ
    -0.08
    alen
    -0.08
    POSITIVE LOGITS
     cut
    0.09
     cutter
    0.09
    cut
    0.09
    :
    0.09
    enty
    0.09
    etu
    0.08
    имÑĥ
    0.08
    etter
    0.08
     Hun
    0.08
    uters
    0.08
    Activations Density 0.000%

    No Known Activations