© 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. 62224
    Prev
    Next
    INDEX
    Explanations

    phthalates, phthalic, pharyngeal, phantasthma, phthalimide

    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
     Copp
    -0.09
    richt
    -0.09
     toast
    -0.09
     ow
    -0.08
     Cecil
    -0.08
    ICE
    -0.08
    edo
    -0.08
     Vocal
    -0.08
    urance
    -0.08
     Called
    -0.08
    POSITIVE LOGITS
     Ph
    0.26
     ph
    0.21
    Ph
    0.20
    /ph
    0.15
    .ph
    0.15
    (ph
    0.14
    ph
    0.14
    phan
    0.14
    .Ph
    0.13
    -ph
    0.12
    Activations Density 0.108%

    No Known Activations