© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44465
    Prev
    Next
    INDEX
    Explanations

    syntax and code structure

    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
    èĥ½å¤Ł
    -0.11
     å°Ĩ
    -0.10
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
    endar
    -0.09
    ipp
    -0.09
    linkplain
    -0.09
     bÄĻd
    -0.09
    å°ĩ
    -0.09
     allowing
    -0.09
    ãģ«ãĤĪãģ£ãģ¦
    -0.08
    POSITIVE LOGITS
     dign
    0.09
     address
    0.09
    chg
    0.09
     outr
    0.09
     ëĶ°ë¥¸
    0.09
    axed
    0.08
    iegel
    0.08
     fines
    0.08
    оÑĤÑĮ
    0.08
     ÃŃch
    0.08
    Activations Density 0.222%

    No Known Activations