© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35258
    Prev
    Next
    INDEX
    Explanations

    ÑĤекÑģÑĤ пÑĢиказа ÑģабоÑĤе

    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
     поба
    -0.12
     заболева
    -0.12
     индивидÑĥ
    -0.12
     завиÑģим
    -0.11
    wnd
    -0.11
     заÑıв
    -0.10
     заÑıви
    -0.10
     Ðŀдна
    -0.10
     зави
    -0.10
     имÑĥ
    -0.10
    POSITIVE LOGITS
     иÑģполÑĮзовани
    0.16
    âĦĸâĦĸ
    0.11
     Ñģ
    0.11
    ±Ð¾ÑĤ
    0.10
    надлеж
    0.09
    shr
    0.09
     scant
    0.09
    azy
    0.09
    Ñģ
    0.09
     Cage
    0.09
    Activations Density 0.133%

    No Known Activations