© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 17265
    Prev
    Next
    INDEX
    Explanations

    design, write, hack, program, discuss, go

    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
     ner
    -0.10
     pop
    -0.10
     alarm
    -0.10
     stat
    -0.09
    arium
    -0.09
    æīįèĥ½
    -0.09
     oppos
    -0.09
    nero
    -0.09
    ego
    -0.09
     Shan
    -0.09
    POSITIVE LOGITS
    avis
    0.11
    325
    0.10
     Aviv
    0.09
     writ
    0.09
     Holt
    0.09
    ué
    0.08
    uer
    0.08
    аÑĤкÑĥ
    0.08
     itr
    0.08
    åģļ
    0.08
    Activations Density 0.222%

    No Known Activations