© 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. 34645
    Prev
    Next
    INDEX
    Explanations

    element analysis, Asset class

    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
    ÂĢÂĢ
    -0.11
    ¶Į
    -0.10
    ¦æĥħ
    -0.08
    ıa
    -0.08
    Occurred
    -0.08
     zdrav
    -0.08
    ToDevice
    -0.08
    atürk
    -0.08
    Âģ@
    -0.08
    -wsj
    -0.07
    POSITIVE LOGITS
     ​​
    0.09
    0.09
     ëĭ¤ìļ´ë°Ľê¸°
    0.07
    ãİ
    0.07
     /
    0.07
     setBackgroundImage
    0.07
    hend
    0.06
     geliÅŁ
    0.06
     (
    0.06
     @
    0.06
    Activations Density 2.460%

    No Known Activations