© 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. 64813
    Prev
    Next
    INDEX
    Explanations

    minimum length specifications

    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
    éĺħ读次æķ°
    -0.09
    ãĥ³ãĤ¯
    -0.09
    styleType
    -0.09
     filmer
    -0.09
    Latch
    -0.08
     gypsum
    -0.08
    onen
    -0.08
     crossorigin
    -0.08
     subrange
    -0.08
     lowest
    -0.08
    POSITIVE LOGITS
     length
    0.45
    éķ¿åº¦
    0.38
    length
    0.38
     lengths
    0.36
     Length
    0.35
     дли
    0.34
    -length
    0.34
    _length
    0.33
    Length
    0.32
    .length
    0.31
    Activations Density 0.163%

    No Known Activations