© 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. 64730
    Prev
    Next
    INDEX
    Explanations

    vary widely depending

    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
    imap
    -0.10
    iry
    -0.09
    alsa
    -0.09
    ersh
    -0.09
     meas
    -0.09
     variants
    -0.09
    ucer
    -0.09
     massively
    -0.09
    ¦Ĥ
    -0.09
    aln
    -0.09
    POSITIVE LOGITS
     depending
    0.24
     widely
    0.22
    depending
    0.19
     Depending
    0.16
    Depending
    0.14
    ingly
    0.13
     degrees
    0.13
     Wid
    0.13
     wide
    0.12
    wide
    0.11
    Activations Density 0.017%

    No Known Activations