© 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. 37631
    Prev
    Next
    INDEX
    Explanations

    understand and explain

    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
    Normalization
    -0.09
     assim
    -0.09
     drum
    -0.09
    ught
    -0.09
     hei
    -0.09
     Schro
    -0.08
    ensis
    -0.08
    -REAL
    -0.08
     realism
    -0.08
    _mgmt
    -0.08
    POSITIVE LOGITS
     transparency
    0.18
    explain
    0.17
     transparent
    0.16
     explain
    0.16
    opaque
    0.15
    -transparent
    0.15
     Explain
    0.15
     opaque
    0.14
    éĢı
    0.14
    transparent
    0.13
    Activations Density 0.080%

    No Known Activations