© 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. 58953
    Prev
    Next
    INDEX
    Explanations

    header id assistant Mah sage

    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
     Baba
    -0.12
     Hari
    -0.11
     Amit
    -0.11
     Mob
    -0.11
     Monument
    -0.10
    backup
    -0.10
     Sof
    -0.10
     vinegar
    -0.10
     Fen
    -0.09
     pockets
    -0.09
    POSITIVE LOGITS
     Ind
    0.13
     Mats
    0.13
     Rud
    0.12
     Dra
    0.12
     yak
    0.12
    ä¼
    0.12
     Dev
    0.12
     vyu
    0.11
     Ling
    0.11
     Van
    0.11
    Activations Density 0.045%

    No Known Activations