© 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. 18613
    Prev
    Next
    INDEX
    Explanations

    end of the person's, variation, preferences

    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
    #
    -0.10
     )\n\n\n\n\n\n\n\n
    -0.10
    953
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     तह
    -0.08
    using
    -0.07
     :\n\n\n\n
    -0.07
    -âĢIJ
    -0.07
    ãĢĢ ãĢĢ ãĢĢ
    -0.07
     pornost
    -0.07
    POSITIVE LOGITS
     amore
    0.09
    æĽ´åĬł
    0.09
    âĶ¬
    0.08
    nia
    0.08
    ]._
    0.08
     ساÛĮر
    0.08
    .RELATED
    0.08
     larg
    0.08
    Åĺ
    0.08
     suit
    0.07
    Activations Density 0.738%

    No Known Activations