Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65403
    Prev
    Next
    INDEX
    Explanations

    representar etapas de projeto

    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
     follando
    -0.09
     differentiated
    -0.09
     venda
    -0.09
    kf
    -0.09
    ummer
    -0.09
     mo
    -0.09
    .Mode
    -0.08
     podmÃŃnky
    -0.08
    amus
    -0.08
     coquine
    -0.08
    POSITIVE LOGITS
     cycle
    0.11
     risks
    0.10
     Permanent
    0.10
     Cycle
    0.10
    portun
    0.10
    ÌĤ
    0.10
     ries
    0.10
     planning
    0.09
     Performance
    0.09
     subprocess
    0.09
    Activations Density 0.189%

    No Known Activations