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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38869
    Prev
    Next
    INDEX
    Explanations

    requires specialized knowledge

    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
     less
    -0.11
     Certif
    -0.10
    onus
    -0.09
     ï½°
    -0.09
     relatively
    -0.09
     Cuisine
    -0.09
     unprecedented
    -0.08
     ``
    -0.08
     ultimate
    -0.08
     Greatest
    -0.08
    POSITIVE LOGITS
     expertise
    0.20
     expert
    0.15
     knowledge
    0.15
     chuyên
    0.14
    ä¸ĵä¸ļ
    0.14
    expert
    0.13
     experts
    0.13
     training
    0.12
     specialist
    0.12
     years
    0.12
    Activations Density 0.107%

    No Known Activations