© 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. 64680
    Prev
    Next
    INDEX
    Explanations

    SCP serial numbers, especially 001

    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
    Negative Logits
     Ey
    -0.10
     Cannon
    -0.09
     cdr
    -0.09
    amel
    -0.09
     Herb
    -0.09
     +
    -0.08
     PR
    -0.08
     LIC
    -0.08
     Hancock
    -0.08
     Getter
    -0.08
    POSITIVE LOGITS
    .Serial
    0.10
    ¶Į
    0.10
    ras
    0.09
    æ´¥
    0.09
    ıa
    0.09
    -prepend
    0.08
    curacy
    0.08
    ******č\n
    0.08
    ³ç´°
    0.08
    ¦æĥħ
    0.08
    Activations Density 0.096%

    No Known Activations