© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    variable declarations: char, string, int, array

    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
    ··
    -0.11
     #
    -0.09
     Glob
    -0.09
     Constantin
    -0.09
    cmds
    -0.08
    706
    -0.08
    umi
    -0.08
     int
    -0.08
    iry
    -0.08
    alars
    -0.08
    POSITIVE LOGITS
     temp
    0.13
    ((*
    0.12
     TempData
    0.11
    temp
    0.11
     Temp
    0.10
     buffer
    0.10
     PROGMEM
    0.10
     overthrow
    0.10
     tmp
    0.10
     buf
    0.10
    Activations Density 0.047%

    No Known Activations