© 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. 29018
    Prev
    Next
    INDEX
    Explanations

    not a, is not

    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
    并ä¸į
    -0.18
     nicht
    -0.17
     não
    -0.16
    ä¸įè¦ģ
    -0.16
     không
    -0.16
    à¹Ħม
    -0.15
     tidak
    -0.15
     no
    -0.15
     not
    -0.14
     nothing
    -0.14
    POSITIVE LOGITS
     instead
    0.25
     naopak
    0.21
     sondern
    0.21
     Nor
    0.21
     Instead
    0.21
     nor
    0.21
    nor
    0.20
    Instead
    0.19
     بÙĦÚ©Ùĩ
    0.18
    instead
    0.18
    Activations Density 0.178%

    No Known Activations