© 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. 33814
    Prev
    Next
    INDEX
    Explanations

    no internet access

    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
     brush
    -0.11
    lify
    -0.10
    plode
    -0.10
     ifndef
    -0.09
    uppy
    -0.09
     Brig
    -0.09
     Hollow
    -0.09
     Brush
    -0.09
    yal
    -0.09
    Å
    -0.08
    POSITIVE LOGITS
     internet
    0.24
     Internet
    0.23
    Internet
    0.19
    internet
    0.17
     real
    0.16
    äºĴèģĶç½ij
    0.16
     direct
    0.14
     пÑĢÑıм
    0.13
     realtime
    0.12
    缴æİ¥
    0.12
    Activations Density 0.114%

    No Known Activations