© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    politics, sabotage

    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
     Wahl
    -0.10
     Contact
    -0.09
     Tus
    -0.09
     Greenwood
    -0.09
     æѦ
    -0.09
     society
    -0.09
     brib
    -0.09
    itchens
    -0.09
    æī§
    -0.08
     recruitment
    -0.08
    POSITIVE LOGITS
     politics
    0.24
     Politics
    0.19
     political
    0.16
     cli
    0.15
    Politics
    0.14
     office
    0.14
     Political
    0.13
    æĶ¿æ²»
    0.13
     Mach
    0.13
     polit
    0.13
    Activations Density 0.108%

    No Known Activations