© 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. 24645
    Prev
    Next
    INDEX
    Explanations

    process and object

    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
    .scalablytyped
    -0.09
     Fist
    -0.09
    FLT
    -0.08
    enant
    -0.08
     Tos
    -0.08
    adata
    -0.08
     Dez
    -0.08
     rost
    -0.08
     Freight
    -0.08
    158
    -0.08
    POSITIVE LOGITS
    ãģĿãģĵ
    0.13
    éĤ£éĩĮ
    0.13
     THAT
    0.11
     Ø°ÙĦÙĥ
    0.10
     Äijó
    0.10
     them
    0.10
    åħ¶ä¸Ń
    0.10
    åĽŀæĿ¥
    0.10
     ê·¸ê²ĥ
    0.09
     That
    0.09
    Activations Density 0.115%

    No Known Activations