© 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. 34355
    Prev
    Next
    INDEX
    Explanations

    author: genre:I want

    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
     Louis
    -0.08
     Sy
    -0.08
    ore
    -0.07
    ãĥ¼ãĥ¼
    -0.07
     Eng
    -0.07
    ictionaries
    -0.07
    âĢĮ
    -0.07
    ousand
    -0.07
     RO
    -0.07
    Re
    -0.06
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.13
    ëį°ìĿ´íĬ¸
    0.12
    EMPLARY
    0.11
     BÄ°L
    0.11
    IIIK
    0.11
    łéĻ¤
    0.10
    ¦æĥħ
    0.10
     uygu
    0.10
    ******č\n
    0.09
    .***.***
    0.09
    Activations Density 0.304%

    No Known Activations