© 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. 43843
    Prev
    Next
    INDEX
    Explanations

    measures and quantities

    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
    lew
    -0.10
    echa
    -0.10
    centage
    -0.09
    uh
    -0.09
     way
    -0.09
    çĽ
    -0.09
    òa
    -0.09
    quiry
    -0.09
    orama
    -0.08
    arter
    -0.08
    POSITIVE LOGITS
     total
    0.15
     maximum
    0.12
     rating
    0.11
    total
    0.11
     average
    0.11
     minimum
    0.10
     Gund
    0.10
     certain
    0.10
    isin
    0.10
     score
    0.10
    Activations Density 0.089%

    No Known Activations