© 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. 7978
    Prev
    Next
    INDEX
    Explanations

    skills, resources, equipment, experience

    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
     talented
    -0.11
     competent
    -0.10
     expertise
    -0.09
     talents
    -0.09
     competence
    -0.09
     ìłĦ문
    -0.09
     skilled
    -0.08
     talent
    -0.08
     Simpson
    -0.08
    _excel
    -0.08
    POSITIVE LOGITS
     Equipment
    0.14
     resources
    0.14
     equipment
    0.14
     experience
    0.13
     Experience
    0.12
    Equipment
    0.12
    experience
    0.12
    Experience
    0.11
     facilities
    0.10
     commitment
    0.10
    Activations Density 0.064%

    No Known Activations