© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30167
    Prev
    Next
    INDEX
    Explanations

    making generalizations or assumptions

    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
     Humph
    -0.11
    ấp
    -0.08
    umph
    -0.08
     multip
    -0.08
    iente
    -0.08
    /end
    -0.08
    ode
    -0.08
     ä¹
    -0.08
     Kens
    -0.08
     posterior
    -0.08
    POSITIVE LOGITS
     general
    0.38
    general
    0.35
    -general
    0.31
     generalize
    0.31
     général
    0.29
    General
    0.29
     GENERAL
    0.29
     sweeping
    0.29
     General
    0.28
    eneral
    0.28
    Activations Density 0.155%

    No Known Activations