© 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. 56401
    Prev
    Next
    INDEX
    Explanations

    years

    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
     недел
    -0.12
    appa
    -0.10
    ÙIJ
    -0.09
    itud
    -0.09
     gens
    -0.09
    hw
    -0.09
     ÑĤва
    -0.09
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
     огÑĢа
    -0.08
    ollen
    -0.08
    POSITIVE LOGITS
     year
    0.32
     годÑĥ
    0.30
    å¹´
    0.27
     года
    0.25
    year
    0.24
     año
    0.21
    -year
    0.21
     Year
    0.21
    å¹´çļĦ
    0.21
    Year
    0.20
    Activations Density 0.030%

    No Known Activations