© 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. 3195
    Prev
    Next
    INDEX
    Explanations

    trust and others

    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
    èĥİ
    -0.09
    Indented
    -0.09
     समà¤Ŀ
    -0.09
     Stam
    -0.09
    libs
    -0.09
    Denied
    -0.09
    âĹİ
    -0.09
     Wit
    -0.09
     Jad
    -0.08
     Buckingham
    -0.08
    POSITIVE LOGITS
     trust
    0.50
     Trust
    0.40
    Trust
    0.39
    trust
    0.38
     trusts
    0.23
    ä¿¡
    0.23
     ä¿¡
    0.23
     faith
    0.22
     дов
    0.20
     trusting
    0.20
    Activations Density 0.076%

    No Known Activations