© 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. 24732
    Prev
    Next
    INDEX
    Explanations

    human rights and opposition discourse

    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
     teasing
    -0.09
     leftist
    -0.09
     pity
    -0.09
    -Clause
    -0.08
    odos
    -0.08
     socialist
    -0.08
    ebp
    -0.08
     Equal
    -0.08
    oku
    -0.08
     vag
    -0.08
    POSITIVE LOGITS
     diss
    0.24
     human
    0.22
     regime
    0.19
     Human
    0.19
     rights
    0.18
     dissent
    0.18
     prod
    0.18
     Rights
    0.17
     freedom
    0.17
     opposition
    0.17
    Activations Density 0.061%

    No Known Activations