© 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. 37008
    Prev
    Next
    INDEX
    Explanations

    original definition

    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
     далÑĮней
    -0.08
    imei
    -0.08
     rehe
    -0.08
    礼
    -0.07
     ÙĪاÙĦع
    -0.07
    asing
    -0.07
     []:\n
    -0.07
     unmatched
    -0.07
     assists
    -0.07
    .handleError
    -0.07
    POSITIVE LOGITS
     usual
    0.20
     normal
    0.18
    æŃ£å¸¸
    0.16
    usual
    0.14
     original
    0.14
     originally
    0.13
     normally
    0.13
    normal
    0.13
     обÑĭÑĩ
    0.12
     Normal
    0.12
    Activations Density 0.306%

    No Known Activations