© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 20160
    Prev
    Next
    INDEX
    Explanations

    personal use, research, educational

    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
     newbie
    -0.11
     beginner
    -0.11
     pref
    -0.10
    igo
    -0.10
     welcome
    -0.10
     novice
    -0.09
     action
    -0.09
     prefab
    -0.09
     naked
    -0.09
    ï¼ı:
    -0.09
    POSITIVE LOGITS
     hobby
    0.24
     Hobby
    0.21
     research
    0.19
     prot
    0.19
     personal
    0.18
     academic
    0.16
     educational
    0.16
    prot
    0.16
    research
    0.15
    çłĶ究
    0.15
    Activations Density 0.136%

    No Known Activations