© 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. 59388
    Prev
    Next
    INDEX
    Explanations

    помочь вам

    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
     нее
    -0.13
     zástup
    -0.12
     поба
    -0.12
     него
    -0.11
     виÑıв
    -0.11
     заÑıв
    -0.10
    енÑı
    -0.10
     бÑĥма
    -0.10
     ниÑħ
    -0.10
     лÑİдей
    -0.10
    POSITIVE LOGITS
     kepada
    0.22
     индивидÑĥ
    0.20
     мне
    0.18
     вам
    0.18
     dem
    0.16
     Ihnen
    0.16
     емÑĥ
    0.16
     йомÑĥ
    0.15
     лÑİдÑıм
    0.14
     všem
    0.14
    Activations Density 0.099%

    No Known Activations