© 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. 43154
    Prev
    Next
    INDEX
    Explanations

    verbs follow 'and'/'always'/'rain'

    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
    ãģķãĤĮãģ¦ãģĦãĤĭ
    -0.13
     been
    -0.12
     taken
    -0.12
    thrown
    -0.12
     flown
    -0.11
    ãĤīãĤĮãģ¦ãģĦãĤĭ
    -0.11
     Taken
    -0.10
     blown
    -0.10
     drawn
    -0.10
    ãĤĮãģ¦ãģĦãĤĭ
    -0.10
    POSITIVE LOGITS
     gave
    0.20
    ноÑģи
    0.16
    лÑıли
    0.16
    æĿ¥äºĨ
    0.15
     took
    0.15
     went
    0.15
    åĪ°äºĨ
    0.15
     grew
    0.15
     داد
    0.14
    ä¸ĬäºĨ
    0.14
    Activations Density 0.255%

    No Known Activations