© 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. 50111
    Prev
    Next
    INDEX
    Explanations

    amount of matter

    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
     Bret
    -0.12
    935
    -0.10
     cent
    -0.10
     ineff
    -0.09
     intact
    -0.09
    ãĥ³ãĤº
    -0.09
    cko
    -0.09
     Scient
    -0.09
     sem
    -0.09
     safe
    -0.09
    POSITIVE LOGITS
     matter
    0.20
     mass
    0.19
    matter
    0.17
     density
    0.15
     маÑģÑģ
    0.15
     distribution
    0.15
     Matter
    0.14
     substance
    0.14
     concentration
    0.13
     sources
    0.13
    Activations Density 0.069%

    No Known Activations