© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    combine, join, merge, unite

    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
     concatenated
    -0.12
     intertwined
    -0.12
     Mutual
    -0.11
     relationships
    -0.09
    Relation
    -0.09
    丶
    -0.09
     Partnership
    -0.09
     Shared
    -0.09
     friendships
    -0.09
     Companion
    -0.08
    POSITIVE LOGITS
    åIJĪ
    0.28
     combination
    0.26
     join
    0.24
     union
    0.23
     joining
    0.23
     åIJĪ
    0.22
     combine
    0.22
    ç»ĵåIJĪ
    0.22
     íķ©
    0.22
    .merge
    0.21
    Activations Density 0.209%

    No Known Activations