© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24869
    Prev
    Next
    INDEX
    Explanations

    possibility or being"""

    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
    -0.17
     завиÑģим
    -0.14
     заболева
    -0.14
     диви
    -0.12
     недел
    -0.11
     имÑĥ
    -0.11
     заÑıви
    -0.11
     заÑıв
    -0.10
    заб
    -0.10
     pij
    -0.10
    POSITIVE LOGITS
     byÄĩ
    0.18
     бÑĭÑĤÑĮ
    0.15
     essere
    0.15
     être
    0.14
     being
    0.14
    être
    0.14
    owaÄĩ
    0.13
     být
    0.12
    被
    0.12
     pocházet
    0.12
    Activations Density 0.057%

    No Known Activations