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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45212
    Prev
    Next
    INDEX
    Explanations

    therefore or so

    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
     consequ
    -0.10
    kah
    -0.10
     CONSEQUENTIAL
    -0.09
     consequential
    -0.09
     consequences
    -0.09
    ï¼Įä¸įè¿ĩ
    -0.09
     Conversely
    -0.08
    ä¸įè¿ĩ
    -0.08
    -0.08
     Ridley
    -0.08
    POSITIVE LOGITS
     therefore
    0.51
     Therefore
    0.47
    Therefore
    0.44
    æīĢ以
    0.43
    ï¼ĮæīĢ以
    0.42
     donc
    0.36
     wiÄĻc
    0.36
     поÑįÑĤомÑĥ
    0.36
    ï¼ĮåĽłæѤ
    0.34
     So
    0.33
    Activations Density 0.101%

    No Known Activations