© 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. 40640
    Prev
    Next
    INDEX
    Explanations

    how can do

    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
    uste
    -0.09
    yle
    -0.09
     tem
    -0.09
     поÑĩемÑĥ
    -0.09
     tent
    -0.09
     Thomson
    -0.08
    934
    -0.08
    ToString
    -0.08
    433
    -0.08
    ignum
    -0.08
    POSITIVE LOGITS
     puedo
    0.18
     can
    0.16
    æīįèĥ½
    0.16
    åı¯ä»¥
    0.15
     should
    0.15
     dapat
    0.14
    should
    0.13
     можно
    0.12
     Should
    0.12
     tôi
    0.12
    Activations Density 0.115%

    No Known Activations