© 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. 46538
    Prev
    Next
    INDEX
    Explanations

    wealth, God, Kong

    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
    als
    -0.09
    228
    -0.09
     until
    -0.09
    TTY
    -0.08
     till
    -0.08
    rak
    -0.08
    -chan
    -0.08
    _lng
    -0.08
     Fav
    -0.08
    rics
    -0.08
    POSITIVE LOGITS
    ê±°ëĤĺ
    0.10
    ebek
    0.09
    ãĤĬãģ¨
    0.09
    åıĬåħ¶
    0.09
    ãģĻãģĻ
    0.09
    ARIO
    0.08
     íĺ¹
    0.08
    dle
    0.08
    Gratis
    0.08
    ingle
    0.08
    Activations Density 0.071%

    No Known Activations