© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 9435
    Prev
    Next
    INDEX
    Explanations

    studies found that

    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
     studies
    -0.12
     research
    -0.12
     Statistics
    -0.10
    izont
    -0.09
     Studies
    -0.09
    tin
    -0.09
    ú
    -0.09
    inese
    -0.08
    udi
    -0.08
    research
    -0.08
    POSITIVE LOGITS
     exposure
    0.14
     Exposure
    0.12
     .ï¼ı
    0.11
     Links
    0.11
     certain
    0.11
    adding
    0.11
    Links
    0.10
     receipt
    0.10
    ceipt
    0.09
     interventions
    0.09
    Activations Density 0.089%

    No Known Activations