© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    teamwork and investment syndicates

    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
     reordered
    -0.12
     singly
    -0.11
    ican
    -0.10
     Talks
    -0.09
    avl
    -0.09
     cooperating
    -0.09
     clos
    -0.09
     trif
    -0.09
     pairing
    -0.09
     concaten
    -0.09
    POSITIVE LOGITS
     group
    0.33
     shared
    0.32
    shared
    0.27
     team
    0.27
     collective
    0.27
    åħ±
    0.24
     åħ±
    0.24
     ê³µëıĻ
    0.23
    åħ±åIJĮ
    0.23
    group
    0.23
    Activations Density 0.248%

    No Known Activations