© 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. 59063
    Prev
    Next
    INDEX
    Explanations

    patterns, trends, relationships

    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
    .printStackTrace
    -0.11
     Legs
    -0.09
    rieve
    -0.09
    cum
    -0.09
     ance
    -0.08
    paralleled
    -0.08
    chem
    -0.08
     Mun
    -0.08
     pawn
    -0.08
    hx
    -0.08
    POSITIVE LOGITS
     pattern
    0.15
     relationships
    0.15
     relationship
    0.13
     trends
    0.13
     Pattern
    0.12
     trend
    0.12
     patterns
    0.12
     structure
    0.12
     connections
    0.12
    Relationship
    0.11
    Activations Density 0.034%

    No Known Activations