© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26596
    Prev
    Next
    INDEX
    Explanations

    making a positive difference

    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
    Not in Any Lists

    No Comments

    Negative Logits
    499
    -0.09
    ensa
    -0.09
    §è¡Į
    -0.09
    )const
    -0.08
    гоÑĤ
    -0.08
    ALAR
    -0.08
    cko
    -0.08
     Spor
    -0.08
    alar
    -0.08
     tic
    -0.08
    POSITIVE LOGITS
     makes
    0.40
     make
    0.40
     making
    0.38
     difference
    0.33
     Makes
    0.33
    makes
    0.33
    make
    0.32
    Makes
    0.30
     membuat
    0.30
     Making
    0.29
    Activations Density 0.068%

    No Known Activations