© 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. 35868
    Prev
    Next
    INDEX
    Explanations

    character traits and dynamics

    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
     impr
    -0.09
    ãĥ¬ãĥĥãĥĪ
    -0.09
     ado
    -0.09
     caffeine
    -0.09
    à¸ĸม
    -0.09
     Grove
    -0.09
     Marvin
    -0.09
    cased
    -0.08
    iec
    -0.08
    باش
    -0.08
    POSITIVE LOGITS
     interesting
    0.22
    interesting
    0.18
     tension
    0.16
    Interesting
    0.16
     dynamics
    0.15
     opportunities
    0.15
     interess
    0.15
     dynamic
    0.14
     Dynamics
    0.14
     Interesting
    0.14
    Activations Density 0.064%

    No Known Activations