© 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. 38460
    Prev
    Next
    INDEX
    Explanations

    D option identifier

    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
    971
    -0.10
    ãĥ¥
    -0.09
    uta
    -0.09
    stvo
    -0.09
     bree
    -0.09
    aya
    -0.08
     Alexand
    -0.08
    ETH
    -0.08
     showc
    -0.08
     Blaze
    -0.08
    POSITIVE LOGITS
     none
    0.15
    None
    0.15
     None
    0.15
    none
    0.13
     choices
    0.12
    _none
    0.11
     option
    0.11
    .option
    0.11
    :none
    0.11
    choices
    0.11
    Activations Density 0.050%

    No Known Activations