© 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. 25409
    Prev
    Next
    INDEX
    Explanations

    would likely have a significant impact

    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
    ï½ľ
    -0.09
    å§ĭ
    -0.09
     increasingly
    -0.09
     impro
    -0.09
    è¶Ĭ
    -0.09
    580
    -0.09
    spath
    -0.09
     Increasing
    -0.09
     sometimes
    -0.09
     Sometimes
    -0.09
    POSITIVE LOGITS
     would
    0.21
     likely
    0.19
    would
    0.19
     Would
    0.17
    likely
    0.16
    Would
    0.15
     initially
    0.14
     serait
    0.14
     würde
    0.14
    arÃŃa
    0.14
    Activations Density 0.100%

    No Known Activations