© 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. 49419
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and interpretation

    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
    ÂĢÂĢ
    -0.09
    forcements
    -0.09
    ://{
    -0.09
    ennie
    -0.09
    endencies
    -0.09
    ä¼ı
    -0.09
    ttp
    -0.08
    subclass
    -0.08
    xit
    -0.08
    Persistence
    -0.08
    POSITIVE LOGITS
     meaning
    0.19
     truth
    0.17
     knowledge
    0.16
     understanding
    0.16
     possibility
    0.15
     thought
    0.15
     discovery
    0.15
     Truth
    0.14
     inquiry
    0.14
     learning
    0.14
    Activations Density 0.114%

    No Known Activations