© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    asking for personal background and interests

    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
     Themes
    -0.10
    ueva
    -0.09
    peare
    -0.09
     dahi
    -0.09
    ￣￣￣
    -0.08
     neod
    -0.08
    \Id
    -0.08
    à¸ļà¸Ħ
    -0.08
    USTER
    -0.08
     ÄijÃŃch
    -0.08
    POSITIVE LOGITS
     hobbies
    0.15
     plans
    0.15
     interests
    0.15
    趣
    0.14
     favorite
    0.14
     weekend
    0.13
     interesting
    0.13
     occupation
    0.13
     work
    0.12
     Plans
    0.12
    Activations Density 0.120%

    No Known Activations