© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23944
    Prev
    Next
    INDEX
    Explanations

    even in negative statements

    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
    ught
    -0.11
     hog
    -0.09
     Hog
    -0.09
    bery
    -0.09
    anic
    -0.09
     Sok
    -0.09
    atak
    -0.09
    perse
    -0.09
    abin
    -0.08
    osi
    -0.08
    POSITIVE LOGITS
     even
    0.16
     remot
    0.15
    -handed
    0.13
     remotely
    0.13
    even
    0.13
     begin
    0.12
     dign
    0.12
     близ
    0.11
     mesmo
    0.11
     near
    0.11
    Activations Density 0.026%

    No Known Activations