© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30538
    Prev
    Next
    INDEX
    Explanations

    transitions to new thoughts

    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
     ìĿ´ìłľ
    -0.09
    ä¸įå¾Ĺ
    -0.09
    culus
    -0.08
    .SelectedIndex
    -0.08
    634
    -0.08
    ´:
    -0.08
    ãģ©ãģĨ
    -0.08
    "Now
    -0.08
    forman
    -0.08
     foremost
    -0.08
    POSITIVE LOGITS
     maybe
    0.25
     let
    0.24
     perhaps
    0.21
     lets
    0.20
     Maybe
    0.20
    maybe
    0.18
    Maybe
    0.18
     Perhaps
    0.17
    Perhaps
    0.16
     vielleicht
    0.16
    Activations Density 0.078%

    No Known Activations