© 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. 40753
    Prev
    Next
    INDEX
    Explanations

    substituted carboxylic acids

    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
    isu
    -0.09
     ï½°
    -0.08
    hea
    -0.08
    esModule
    -0.08
     hous
    -0.08
    ilit
    -0.08
     DT
    -0.08
    olib
    -0.08
     Ñģон
    -0.08
     dos
    -0.08
    POSITIVE LOGITS
    âĶģâĶģ
    0.11
     CAS
    0.11
     Pub
    0.09
    Pub
    0.09
    zure
    0.09
     pageCount
    0.08
    âĶģ
    0.08
    ADO
    0.08
    sob
    0.08
    ocab
    0.08
    Activations Density 0.091%

    No Known Activations