© 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. 44127
    Prev
    Next
    INDEX
    Explanations

    offering support and guidance

    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
     zel
    -0.11
     goodwill
    -0.11
     rewarding
    -0.11
     sing
    -0.10
     fing
    -0.09
     благ
    -0.09
    ango
    -0.09
    icho
    -0.09
     Hector
    -0.09
     bri
    -0.09
    POSITIVE LOGITS
     support
    0.24
     shoulder
    0.23
     Shoulder
    0.20
     listening
    0.18
    èĤ©
    0.17
     shoulders
    0.16
     Listening
    0.16
    support
    0.16
     Support
    0.15
    æĶ¯æĮģ
    0.15
    Activations Density 0.064%

    No Known Activations