© 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. 35432
    Prev
    Next
    INDEX
    Explanations

    conflict between two parts

    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
    andom
    -0.10
    uvw
    -0.09
     belie
    -0.09
     ï¾Ħ
    -0.08
    lor
    -0.08
     Tran
    -0.08
    awns
    -0.08
     unic
    -0.08
    uum
    -0.08
    intendent
    -0.08
    POSITIVE LOGITS
     aspects
    0.13
     aspect
    0.13
     Jung
    0.12
     fears
    0.12
     parts
    0.12
     recently
    0.12
     currently
    0.12
     current
    0.11
     recent
    0.11
     наÑıв
    0.11
    Activations Density 0.039%

    No Known Activations