© 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. 55259
    Prev
    Next
    INDEX
    Explanations

    it followed by a verb

    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
    aign
    -0.09
    ové
    -0.09
     themselves
    -0.09
     yourselves
    -0.09
    874
    -0.08
     Meh
    -0.08
    /current
    -0.08
    hill
    -0.08
     ///<
    -0.08
     Homework
    -0.08
    POSITIVE LOGITS
    iner
    0.27
    chy
    0.24
    unes
    0.20
    /he
    0.17
    åĢij
    0.16
    zelf
    0.16
    /she
    0.15
    SELF
    0.14
    self
    0.14
    inerary
    0.14
    Activations Density 0.105%

    No Known Activations