© 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. 48853
    Prev
    Next
    INDEX
    Explanations

    is responsible for

    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
    adesh
    -0.09
     Installer
    -0.09
    joy
    -0.09
    illance
    -0.08
     ä¸
    -0.08
     ad
    -0.08
     intimate
    -0.08
    èĩ¨
    -0.08
     intimately
    -0.08
    eden
    -0.08
    POSITIVE LOGITS
     responsible
    0.64
     Responsible
    0.47
     responsable
    0.46
    è´Łè´£
    0.44
    ponsible
    0.43
     respons
    0.39
     responsibility
    0.38
     оÑĤвеÑĤÑģÑĤвен
    0.31
     sorumlu
    0.31
     RESPONS
    0.30
    Activations Density 0.150%

    No Known Activations