© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 274
    Prev
    Next
    INDEX
    Explanations

    craftsmanship and artisanal skills

    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
     WTF
    -0.11
     paint
    -0.09
     sleeve
    -0.09
     Scrap
    -0.09
    PLE
    -0.09
     mange
    -0.09
    LD
    -0.09
    mgr
    -0.08
    nel
    -0.08
     engineers
    -0.08
    POSITIVE LOGITS
     skill
    0.21
     craft
    0.20
     skills
    0.19
    æĬĢèĥ½
    0.18
     Skills
    0.17
     handic
    0.17
    skills
    0.17
     Skill
    0.16
     tradition
    0.16
    Skill
    0.16
    Activations Density 0.067%

    No Known Activations