© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21348
    Prev
    Next
    INDEX
    Explanations

    having personal opinions

    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
    iyeti
    -0.10
    Reviewer
    -0.09
    605
    -0.09
    ovel
    -0.09
     disposed
    -0.09
    igo
    -0.09
     lifetime
    -0.08
    lesi
    -0.08
     motivations
    -0.08
    аÑĪа
    -0.08
    POSITIVE LOGITS
     opinion
    0.51
     opinions
    0.46
     Opinion
    0.41
     opin
    0.41
     Op
    0.34
    æĦıè§ģ
    0.29
    Op
    0.29
     views
    0.26
     op
    0.23
    Views
    0.22
    Activations Density 0.165%

    No Known Activations