© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    escape from

    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
    ãĢĥ
    -0.11
    ãĢĢï¾ŀ
    -0.09
     Jerome
    -0.09
     inability
    -0.09
     Bren
    -0.09
     issue
    -0.09
    Failure
    -0.09
    иÑģÑĮ
    -0.09
     overhead
    -0.09
    алÑİ
    -0.09
    POSITIVE LOGITS
     grips
    0.16
     bonds
    0.16
     alive
    0.14
    avery
    0.14
     grip
    0.13
     jaws
    0.13
     grasp
    0.13
     khá»ıi
    0.13
    utches
    0.13
    æĿŁ
    0.13
    Activations Density 0.033%

    No Known Activations