© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 40690
    Prev
    Next
    INDEX
    Explanations

    returning or moving 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
    -0.11
    Backend
    -0.11
     frontend
    -0.09
    roman
    -0.09
    arel
    -0.09
     Front
    -0.09
    /frontend
    -0.08
     Backpack
    -0.08
     retali
    -0.08
    Forward
    -0.08
    POSITIVE LOGITS
     return
    0.62
    åĽŀåĪ°
    0.57
     returned
    0.54
     returning
    0.53
    return
    0.49
     back
    0.49
    æĪ»
    0.49
     returns
    0.49
    è¿ĶåĽŀ
    0.48
     terug
    0.46
    Activations Density 0.128%

    No Known Activations