© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    specialty chemicals

    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
    chie
    -0.09
    ivan
    -0.09
     gratuitement
    -0.09
    bservice
    -0.09
    atha
    -0.09
    ieten
    -0.08
     herr
    -0.08
    arl
    -0.08
     treff
    -0.08
    edException
    -0.08
    POSITIVE LOGITS
     such
    0.13
     applications
    0.10
    such
    0.10
     division
    0.09
     used
    0.09
    Ｌ
    0.09
     Applications
    0.09
     sector
    0.09
     segment
    0.09
    des
    0.08
    Activations Density 0.056%

    No Known Activations