© 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. 37258
    Prev
    Next
    INDEX
    Explanations

    content requirements and instructions

    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
     coincide
    -0.11
     Ùħشار
    -0.08
    éĥ½ä¼ļ
    -0.08
    kontakte
    -0.08
     pending
    -0.08
     coincidence
    -0.08
    ekim
    -0.08
     Socorro
    -0.08
    .EOF
    -0.08
     ilma
    -0.08
    POSITIVE LOGITS
     contain
    0.18
     be
    0.15
    contain
    0.14
     contains
    0.14
     containing
    0.12
     ÑģодеÑĢж
    0.12
    ering
    0.12
     ends
    0.12
     chứa
    0.12
     Ends
    0.11
    Activations Density 0.105%

    No Known Activations