© 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. 25156
    Prev
    Next
    INDEX
    Explanations

    social justice, oracle readings, freelance work, military operations

    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
     kidn
    -0.10
     Ernest
    -0.09
    estead
    -0.09
    è²ł
    -0.09
    blings
    -0.09
    irical
    -0.09
     jog
    -0.09
    403
    -0.09
    oda
    -0.08
    amen
    -0.08
    POSITIVE LOGITS
    ivism
    0.15
    manship
    0.15
    anship
    0.14
    ÅĪovánÃŃ
    0.14
    ávánÃŃ
    0.14
    ÑİваннÑı
    0.14
    ming
    0.14
    iscing
    0.13
    ovánÃŃ
    0.13
    nictvÃŃ
    0.13
    Activations Density 0.237%

    No Known Activations