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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37713
    Prev
    Next
    INDEX
    Explanations

    maybe or perhaps

    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
    inue
    -0.11
    aller
    -0.10
    lop
    -0.10
    inine
    -0.09
     probably
    -0.09
    anga
    -0.09
    inea
    -0.09
    lya
    -0.09
    elling
    -0.09
    815
    -0.09
    POSITIVE LOGITS
    /pro
    0.19
    ily
    0.14
    -être
    0.13
    hood
    0.13
    haps
    0.13
    ารย
    0.13
    eee
    0.13
    eeee
    0.11
    hap
    0.11
    .Maybe
    0.11
    Activations Density 0.016%

    No Known Activations