© 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. 25048
    Prev
    Next
    INDEX
    Explanations

    æĪij Korean/Chinese/Russian/Portuguese

    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
    "Yeah
    -0.10
     realpath
    -0.08
     Niet
    -0.08
    imo
    -0.08
     urg
    -0.08
    éĺ³åŁİ
    -0.08
    æľ¬å½ĵãģ«
    -0.08
     bumps
    -0.08
     è£
    -0.08
     Nobel
    -0.07
    POSITIVE LOGITS
     myself
    0.22
    æĪij
    0.20
     æĪij
    0.16
     me
    0.15
    Tôi
    0.15
     tôi
    0.14
    æĺ¯ä¸Ģ个
    0.14
     менÑı
    0.13
     Hello
    0.13
     moi
    0.13
    Activations Density 0.100%

    No Known Activations