© 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. 45395
    Prev
    Next
    INDEX
    Explanations

    generative AI and adversarial networks

    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
    acco
    -0.09
     Administrator
    -0.09
    licity
    -0.09
    spb
    -0.09
    аний
    -0.09
    ingo
    -0.08
    abr
    -0.08
     Vert
    -0.08
    lore
    -0.08
     Dynam
    -0.08
    POSITIVE LOGITS
     advers
    0.16
    ative
    0.11
     models
    0.11
     gener
    0.11
     intent
    0.11
    å¼ı
    0.10
     AI
    0.10
     Gener
    0.09
     Chat
    0.09
     DH
    0.09
    Activations Density 0.024%

    No Known Activations