© 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. 13252
    Prev
    Next
    INDEX
    Explanations

    promising young talent

    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
     experiences
    -0.09
    biz
    -0.09
     entert
    -0.08
    bases
    -0.08
     sophisticated
    -0.08
    彡
    -0.08
    .Arguments
    -0.08
    childs
    -0.08
     sophistic
    -0.08
    kok
    -0.08
    POSITIVE LOGITS
     talent
    0.42
     Talent
    0.31
     talented
    0.29
     talents
    0.28
    tal
    0.25
    人æīį
    0.21
     young
    0.20
     Tal
    0.20
    alent
    0.20
     promising
    0.18
    Activations Density 0.092%

    No Known Activations