© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34865
    Prev
    Next
    INDEX
    Explanations

    about social, significantly expanded, a profound

    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
     wartime
    -0.13
     Army
    -0.09
     Carpenter
    -0.09
    ëĦ
    -0.09
     caffe
    -0.09
     incident
    -0.09
    Army
    -0.09
     army
    -0.09
     patron
    -0.09
    OrElse
    -0.09
    POSITIVE LOGITS
     post
    0.16
     atomic
    0.13
     Hiro
    0.12
    194
    0.12
     Bret
    0.12
     mobil
    0.11
     victory
    0.11
     draft
    0.11
     peace
    0.11
     Axis
    0.11
    Activations Density 0.069%

    No Known Activations