© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33880
    Prev
    Next
    INDEX
    Explanations

    a list or set

    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
     Stub
    -0.12
     solutions
    -0.11
     blur
    -0.10
     Rudy
    -0.09
     Solutions
    -0.09
     Modal
    -0.09
     Markus
    -0.09
     cru
    -0.09
     calendar
    -0.09
     aprove
    -0.08
    POSITIVE LOGITS
     framework
    0.27
     Framework
    0.21
    framework
    0.20
    Framework
    0.20
    æ¡Ĩ
    0.19
    ramework
    0.17
     frameworks
    0.17
    .framework
    0.17
     process
    0.17
    _framework
    0.17
    Activations Density 0.255%

    No Known Activations