© 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. 26291
    Prev
    Next
    INDEX
    Explanations

    handle requests

    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
     Lon
    -0.09
     betr
    -0.09
    adan
    -0.09
     Beh
    -0.08
     streak
    -0.08
     PROP
    -0.08
    angu
    -0.08
    848
    -0.08
    688
    -0.08
     ä¸
    -0.08
    POSITIVE LOGITS
     responsible
    0.26
    è´Łè´£
    0.24
     responsibility
    0.22
     responsable
    0.21
     contain
    0.21
     handle
    0.21
     contains
    0.20
     containing
    0.19
    ponsible
    0.17
     respons
    0.17
    Activations Density 0.045%

    No Known Activations