© 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. 1798
    Prev
    Next
    INDEX
    Explanations

    waiting to finish

    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
    baugh
    -0.09
    nox
    -0.09
    uti
    -0.09
     conquered
    -0.08
     ########.
    -0.08
    empor
    -0.08
    Serialized
    -0.08
     inaug
    -0.08
     sworn
    -0.08
    mite
    -0.08
    POSITIVE LOGITS
     finish
    0.24
     finishes
    0.20
     finished
    0.20
     Finish
    0.18
    Finish
    0.17
    finish
    0.17
     completion
    0.16
     finishing
    0.15
    å®ĮæĪIJ
    0.15
     xong
    0.15
    Activations Density 0.045%

    No Known Activations