© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13715
    Prev
    Next
    INDEX
    Explanations

    the scientific nouns

    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
    ames
    -0.09
    üf
    -0.09
    105
    -0.09
     Rodrig
    -0.09
    iseum
    -0.09
     affiliation
    -0.09
    465
    -0.09
    Ñij
    -0.09
     evac
    -0.08
     обеÑģпеÑĩива
    -0.08
    POSITIVE LOGITS
     prevention
    0.18
     management
    0.18
     protection
    0.16
     design
    0.16
     identification
    0.16
     improvement
    0.16
     treatment
    0.16
     development
    0.15
     creation
    0.15
     study
    0.15
    Activations Density 0.105%

    No Known Activations