© 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. 25720
    Prev
    Next
    INDEX
    Explanations

    a phrase or specifying word

    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
     /
    -0.08
     her
    -0.07
     is
    -0.07
     if
    -0.07
     "---
    -0.07
     my
    -0.07
     –;
    -0.07
    ég
    -0.07
    avel
    -0.07
     ninete
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.11
    ¶Į
    0.09
    ellij
    0.07
    _trampoline
    0.07
    RunWith
    0.07
    heels
    0.07
    .printStackTrace
    0.07
    eç
    0.07
    iento
    0.07
    ï¼¼:
    0.07
    Activations Density 0.840%

    No Known Activations