© 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. 37030
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes followed by prepositions

    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
     because
    -0.23
    because
    -0.18
     поÑĤомÑĥ
    -0.15
    åĽłä¸º
    -0.15
    Because
    -0.14
     Because
    -0.14
     porque
    -0.14
     karena
    -0.14
     omdat
    -0.12
    ï¼ĮåĽłä¸º
    -0.12
    POSITIVE LOGITS
     compared
    0.13
     overall
    0.12
     Compared
    0.10
    overall
    0.10
     indeed
    0.09
    aukee
    0.09
     Kush
    0.09
    对äºİ
    0.09
     despite
    0.09
    ãĤĬãģ¨
    0.09
    Activations Density 0.080%

    No Known Activations