© 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. 11613
    Prev
    Next
    INDEX
    Explanations

    supporting arguments or data

    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
    Not in Any Lists

    No Comments

    Negative Logits
    accur
    -0.10
     accurate
    -0.10
    ResultsController
    -0.09
    ï¿£ï½Ģ
    -0.09
     Beard
    -0.09
    çĥ
    -0.09
     æĺİ
    -0.09
     inaccurate
    -0.09
     substant
    -0.09
     buz
    -0.09
    POSITIVE LOGITS
     weight
    0.14
     Evidence
    0.14
     supporting
    0.13
     strongest
    0.13
     marsh
    0.13
     overwhelming
    0.13
     strength
    0.12
     tipping
    0.12
     evidence
    0.12
     strong
    0.12
    Activations Density 0.050%

    No Known Activations