© 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. 920
    Prev
    Next
    INDEX
    Explanations

    attached, enclosed, attachment

    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
    inh
    -0.09
    ÙĪاء
    -0.09
    Bookmark
    -0.09
     descent
    -0.08
    {:
    -0.08
     Relief
    -0.08
     DISCLAIM
    -0.08
    -neutral
    -0.08
     Morse
    -0.08
    kp
    -0.08
    POSITIVE LOGITS
     attached
    0.16
     enclosed
    0.16
     Attached
    0.13
    Attached
    0.13
    attached
    0.13
     attachment
    0.12
     attach
    0.11
     enclosure
    0.11
     cc
    0.11
     enc
    0.11
    Activations Density 0.309%

    No Known Activations