© 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. 31799
    Prev
    Next
    INDEX
    Explanations

    discovery of shared 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
     remainder
    -0.11
    thic
    -0.11
     Relationships
    -0.10
     relationships
    -0.10
    563
    -0.09
    ools
    -0.09
     sever
    -0.09
     Dia
    -0.09
    hend
    -0.08
     NUM
    -0.08
    POSITIVE LOGITS
     common
    0.34
     shared
    0.28
     interests
    0.24
    common
    0.24
     Common
    0.21
     Shared
    0.21
    shared
    0.21
     COMMON
    0.20
    åħ±åIJĮ
    0.20
     åħ±
    0.20
    Activations Density 0.049%

    No Known Activations