© 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. 19172
    Prev
    Next
    INDEX
    Explanations

    pur prefixes

    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
    ihu
    -0.11
    marsh
    -0.10
    bourg
    -0.10
    alous
    -0.10
    оÑĢож
    -0.09
    ingly
    -0.09
    ocre
    -0.09
    ores
    -0.09
     Shower
    -0.09
     Catch
    -0.09
    POSITIVE LOGITS
     pur
    0.26
     Pur
    0.23
    pur
    0.23
     PUR
    0.18
    CHASE
    0.15
    PUR
    0.15
    _PUR
    0.14
    ification
    0.14
    itan
    0.14
    posed
    0.13
    Activations Density 0.021%

    No Known Activations