© 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. 49087
    Prev
    Next
    INDEX
    Explanations

    (CR 10) notation

    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
    ãģĿãģĹãģ¦
    -0.10
    надлеж
    -0.08
    -0.08
     "
    -0.08
     ou
    -0.08
     Duch
    -0.08
     nomin
    -0.08
    /by
    -0.07
     ,
    -0.07
     Graz
    -0.07
    POSITIVE LOGITS
    ¶Į
    0.12
    łéĻ¤
    0.11
    ogui
    0.09
     hãy
    0.09
     ëĤĺëĬĶ
    0.09
     Äijây
    0.09
     ìļ°ë¦¬ëĬĶ
    0.09
    ायद
    0.09
     please
    0.08
    894
    0.08
    Activations Density 0.351%

    No Known Activations