© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    aye
    -0.09
     Spir
    -0.09
     Wool
    -0.09
     riv
    -0.09
    ury
    -0.08
    |
    -0.08
    eza
    -0.08
    NEL
    -0.08
    åµ
    -0.08
     Sob
    -0.08
    POSITIVE LOGITS
    eks
    0.09
    Configs
    0.09
    ekl
    0.09
    ï½Ŀ
    0.09
    otti
    0.09
     Ludwig
    0.08
     Clair
    0.08
    tod
    0.08
    omik
    0.08
    EMPLARY
    0.08
    Activations Density 0.020%

    No Known Activations