© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    start of canned responses or instructions

    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
    iele
    -0.10
     yer
    -0.10
    ä¹¾
    -0.09
    .rev
    -0.09
    ullen
    -0.09
    çļĦåľ°
    -0.09
    erk
    -0.09
    ModelProperty
    -0.09
    sic
    -0.09
     dad
    -0.08
    POSITIVE LOGITS
     dere
    0.15
     dat
    0.13
    è¾°
    0.13
     plenty
    0.12
    dat
    0.12
     Dere
    0.12
     de
    0.12
    Dat
    0.11
     Plenty
    0.11
     Dat
    0.10
    Activations Density 0.075%

    No Known Activations