© 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. 25790
    Prev
    Next
    INDEX
    Explanations

    symbolic uses of politics

    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
    <|begin_of_text|>
    -0.12
     politicians
    -0.11
     shelter
    -0.09
     commun
    -0.09
    955
    -0.09
     Senator
    -0.09
    unsch
    -0.09
     governments
    -0.09
     Mastery
    -0.09
     hob
    -0.08
    POSITIVE LOGITS
    incinn
    0.11
    .uf
    0.10
    woo
    0.10
     recounts
    0.10
    âĹĭ
    0.10
    amam
    0.09
     Citizens
    0.09
     Bust
    0.09
     LGBT
    0.09
    uger
    0.09
    Activations Density 0.009%

    No Known Activations