© 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. 51740
    Prev
    Next
    INDEX
    Explanations

    "i" + purchase or opinion verbs

    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
     missed
    -0.09
     failing
    -0.09
    âu
    -0.09
    Fetching
    -0.09
    евид
    -0.09
     fucked
    -0.08
    _firestore
    -0.08
    awa
    -0.08
    adm
    -0.08
     nuru
    -0.08
    POSITIVE LOGITS
     purchased
    0.11
     paid
    0.11
     ordered
    0.11
    .scalablytyped
    0.11
     purchase
    0.11
     expectations
    0.10
     rate
    0.10
     Purch
    0.10
     Diss
    0.10
     hÃłi
    0.10
    Activations Density 0.072%

    No Known Activations