© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53537
    Prev
    Next
    INDEX
    Explanations

    quota system, mandatory part, combination of

    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
    大åħ¨
    -0.10
    WithValue
    -0.09
    åIJĪæł¼
    -0.09
    adele
    -0.09
     subsidy
    -0.08
    pac
    -0.08
    enza
    -0.08
     unfinished
    -0.08
     Nich
    -0.08
    FromClass
    -0.08
    POSITIVE LOGITS
     system
    0.27
    åĪ¶åº¦
    0.25
     systems
    0.23
     implemented
    0.21
     sistema
    0.21
     implement
    0.20
    system
    0.20
     sistemi
    0.19
     implementation
    0.19
     système
    0.18
    Activations Density 0.221%

    No Known Activations