© 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. 19376
    Prev
    Next
    INDEX
    Explanations

    SOFTWARE DEVELOPER, high-level, mapping, main, on the Question, will ask

    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
    linkplain
    -0.09
    (íģ¬ê¸°
    -0.09
     Demir
    -0.08
    irket
    -0.08
    exampleInputEmail
    -0.07
    vider
    -0.07
    ekl
    -0.07
     [âĢ¦
    -0.07
     Injector
    -0.07
     Kota
    -0.07
    POSITIVE LOGITS
     müc
    0.08
     inputs
    0.07
    vál
    0.07
     dp
    0.07
     writ
    0.07
     input
    0.07
    erna
    0.07
    ycz
    0.07
    å®Ļ
    0.07
    ķ
    0.06
    Activations Density 5.173%

    No Known Activations