© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 50200
    Prev
    Next
    INDEX
    Explanations

    proactive management and technologies

    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
     protect
    -0.10
     safety
    -0.10
     protection
    -0.10
     åį
    -0.09
     inn
    -0.09
    å®īåħ¨
    -0.09
     quota
    -0.09
     Protect
    -0.09
     protecting
    -0.08
     protected
    -0.08
    POSITIVE LOGITS
     training
    0.22
     Training
    0.17
     regular
    0.17
    training
    0.17
    Training
    0.15
    -training
    0.15
     TRAIN
    0.15
    åŁ¹è®Ń
    0.14
     Regular
    0.14
    regular
    0.14
    Activations Density 0.028%

    No Known Activations