© 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. 51733
    Prev
    Next
    INDEX
    Explanations

    causes and effects

    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
     Weld
    -0.09
     seh
    -0.09
    stract
    -0.08
    porte
    -0.08
    ÑĮко
    -0.08
    atto
    -0.08
    riott
    -0.08
     majority
    -0.08
    hin
    -0.08
     )\n\n\n\n\n\n\n\n
    -0.08
    POSITIVE LOGITS
     because
    0.21
    because
    0.17
    ï¼ĮåĽłä¸º
    0.17
    åĽłä¸º
    0.15
     karena
    0.13
     due
    0.12
     especially
    0.12
    ecause
    0.12
     Because
    0.12
     porque
    0.12
    Activations Density 0.088%

    No Known Activations