© 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. 51387
    Prev
    Next
    INDEX
    Explanations

    continuation and addition

    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
     dit
    -0.11
     inde
    -0.08
    dit
    -0.08
     phenomen
    -0.08
    cca
    -0.08
    çļĦè¯Ŀ
    -0.08
    ãģ¨ãģ¯
    -0.08
     Dit
    -0.08
    kees
    -0.08
    angers
    -0.08
    POSITIVE LOGITS
    etc
    0.22
     etc
    0.21
     also
    0.20
    also
    0.19
     ÑĤакже
    0.16
     także
    0.16
     ayrıca
    0.16
    Also
    0.15
    Additionally
    0.15
     Also
    0.15
    Activations Density 0.158%

    No Known Activations