© 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. 2119
    Prev
    Next
    INDEX
    Explanations

    discovery and finding

    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
    @student
    -0.10
    uated
    -0.10
    oldt
    -0.09
    ensibly
    -0.09
    eration
    -0.09
     lasers
    -0.09
    734
    -0.09
    jeme
    -0.09
    UNC
    -0.08
    ëĮ
    -0.08
    POSITIVE LOGITS
    rir
    0.14
    erto
    0.14
     discovery
    0.13
     discover
    0.13
     discovered
    0.13
    åıijçİ°
    0.13
    ert
    0.12
    erte
    0.12
     Discovery
    0.11
    rim
    0.11
    Activations Density 0.029%

    No Known Activations