© 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. 41613
    Prev
    Next
    INDEX
    Explanations

    controlling or making programs

    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
     passive
    -0.11
     Passive
    -0.10
    712
    -0.09
     Ernst
    -0.09
     pers
    -0.09
    eel
    -0.09
    688
    -0.09
    edo
    -0.09
     Pers
    -0.09
    ako
    -0.09
    POSITIVE LOGITS
     controlling
    0.28
     control
    0.28
    æݧåĪ¶
    0.23
     controls
    0.21
    -control
    0.20
    control
    0.20
     æݧ
    0.20
     Control
    0.18
     kontrol
    0.17
     controle
    0.17
    Activations Density 0.119%

    No Known Activations