© 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. 27399
    Prev
    Next
    INDEX
    Explanations

    suspicion distrust wariness controlling risk

    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
     dissatisfaction
    -0.11
     discontent
    -0.10
     flo
    -0.10
    itung
    -0.10
    adal
    -0.10
    geist
    -0.09
    æģ
    -0.09
    lâm
    -0.09
    rompt
    -0.09
    èį
    -0.09
    POSITIVE LOGITS
     suspicion
    0.38
     suspicious
    0.36
    Susp
    0.31
     suspicions
    0.31
     suspect
    0.30
    istr
    0.30
     Susp
    0.30
     trust
    0.28
     distrust
    0.28
     distr
    0.27
    Activations Density 0.091%

    No Known Activations