© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    quantifiable, measurable, or detectable properties

    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
     unus
    -0.10
     Adapt
    -0.09
     resil
    -0.09
     reh
    -0.09
    éŁ³
    -0.09
     permissible
    -0.09
    recated
    -0.09
     allowable
    -0.09
     proport
    -0.09
     BITTE
    -0.09
    POSITIVE LOGITS
    able
    0.26
    åı¯
    0.21
     easily
    0.21
     ÙĤابÙĦ
    0.19
    itable
    0.19
     able
    0.19
    utable
    0.18
    ABLE
    0.18
    ability
    0.18
    oppable
    0.18
    Activations Density 0.211%

    No Known Activations