© 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. 56426
    Prev
    Next
    INDEX
    Explanations

    considerate, dismissive, empathetic, affectionate

    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
    $MESS
    -0.11
    udence
    -0.10
    isations
    -0.10
    itage
    -0.09
    _notifier
    -0.09
    semblies
    -0.09
    lessly
    -0.09
    icamente
    -0.09
    >NN
    -0.09
    igma
    -0.09
    POSITIVE LOGITS
    ative
    0.17
    able
    0.14
    ive
    0.13
    ful
    0.13
    æĢ§çļĦ
    0.13
    ersive
    0.12
    volent
    0.12
    itive
    0.12
    ATIVE
    0.11
     nature
    0.11
    Activations Density 0.124%

    No Known Activations