© 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. 37638
    Prev
    Next
    INDEX
    Explanations

    never seen before

    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
    ãģĵãģĿ
    -0.09
    _mC
    -0.09
    erli
    -0.09
    IIIK
    -0.08
    æĵ¦
    -0.08
    .Selenium
    -0.08
    GINE
    -0.08
    /apis
    -0.08
     convers
    -0.08
     Alter
    -0.08
    POSITIVE LOGITS
     seen
    0.28
    seen
    0.21
     Seen
    0.21
     anything
    0.19
    Seen
    0.19
     previously
    0.18
     visto
    0.17
     before
    0.17
    è§ģ
    0.17
    anything
    0.16
    Activations Density 0.024%

    No Known Activations