© 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. 379
    Prev
    Next
    INDEX
    Explanations

    helping and developing

    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
    orate
    -0.09
     Smile
    -0.09
     Sail
    -0.08
    ListModel
    -0.08
     ord
    -0.08
     dealing
    -0.08
    ansa
    -0.08
     Daly
    -0.08
    integration
    -0.08
    oningen
    -0.08
    POSITIVE LOGITS
     helping
    0.24
     helps
    0.22
     help
    0.21
     giúp
    0.20
    帮åĬ©
    0.20
    help
    0.20
     ayud
    0.18
     Helps
    0.17
     equip
    0.17
    Help
    0.17
    Activations Density 0.107%

    No Known Activations