© 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. 13785
    Prev
    Next
    INDEX
    Explanations

    used to predict or determine

    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
     ìĿ´ë¥¼
    -0.09
    ưỡng
    -0.08
     vess
    -0.08
    ãĢģãĢĬ
    -0.08
    nee
    -0.08
     ëħ
    -0.08
    ãģ®ãģłãĤįãģĨ
    -0.08
     yalnızca
    -0.08
    IVEN
    -0.07
    978
    -0.07
    POSITIVE LOGITS
     selber
    0.10
     basically
    0.09
     à¤ħà¤Ĺर
    0.08
    à¤Ĭ
    0.08
    ipple
    0.08
    orsch
    0.08
     unle
    0.08
    /perl
    0.08
    ฺ
    0.08
     nackt
    0.08
    Activations Density 0.943%

    No Known Activations