© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 45239
    Prev
    Next
    INDEX
    Explanations

    is example/not

    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
     Meh
    -0.09
    agne
    -0.09
    umatic
    -0.09
    ebi
    -0.08
    atan
    -0.08
    å¦Ĥä¸ĭ
    -0.08
    tery
    -0.08
    vell
    -0.08
    termin
    -0.08
    acer
    -0.08
    POSITIVE LOGITS
     just
    0.28
    åıªæĺ¯
    0.20
    just
    0.20
     merely
    0.19
     juste
    0.18
     only
    0.17
     overs
    0.15
     csak
    0.14
     apenas
    0.13
     sadece
    0.13
    Activations Density 0.009%

    No Known Activations