© 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. 19434
    Prev
    Next
    INDEX
    Explanations

    YouTube channel

    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
     guarante
    -0.08
    en
    -0.08
    .www
    -0.07
    toDate
    -0.07
    a
    -0.07
     Elsa
    -0.07
     intake
    -0.07
     nh
    -0.07
     withd
    -0.07
     -,
    -0.07
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸв
    0.11
    printStats
    0.10
    âĸį
    0.09
    ebek
    0.09
    ÐĴÑĤ
    0.09
    \n\n
    0.09
     -*-č\n
    0.09
    -Allow
    0.09
    âĸĭ
    0.09
    __$
    0.08
    Activations Density 0.000%

    No Known Activations