© 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. 13792
    Prev
    Next
    INDEX
    Explanations

    Twitter acquisition consequences

    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
     facebook
    -0.15
     FB
    -0.14
     Facebook
    -0.13
     fb
    -0.12
    Facebook
    -0.11
    facebook
    -0.11
    FB
    -0.10
    _facebook
    -0.10
    fb
    -0.10
    .facebook
    -0.10
    POSITIVE LOGITS
     Musk
    0.24
     Twitter
    0.18
    Twitter
    0.16
    elon
    0.15
     Dor
    0.14
    /twitter
    0.13
    witter
    0.13
     Tesla
    0.13
     Elon
    0.13
    -twitter
    0.13
    Activations Density 0.035%

    No Known Activations