© 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. 44201
    Prev
    Next
    INDEX
    Explanations

    returning or back

    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
    _backend
    -0.12
    Backend
    -0.09
    aval
    -0.09
     Alv
    -0.09
     rou
    -0.09
    è¾ĵ
    -0.08
     slash
    -0.08
    alive
    -0.08
    лÑıн
    -0.08
    lek
    -0.08
    POSITIVE LOGITS
    åĽŀåĪ°
    0.32
     back
    0.30
     returning
    0.28
    Returning
    0.24
     return
    0.24
    æĪ»
    0.24
     terug
    0.23
     zurück
    0.23
     returns
    0.23
    åĽŀæĿ¥
    0.23
    Activations Density 0.096%

    No Known Activations