© 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. 53233
    Prev
    Next
    INDEX
    Explanations

    safety and sustainability

    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
    Negative Logits
    atz
    -0.10
    iesz
    -0.10
    .:.:.
    -0.10
    _async
    -0.09
    _customize
    -0.09
    .Formatter
    -0.09
    nger
    -0.09
    ãĢĢï½
    -0.09
     丶
    -0.08
    .:.:
    -0.08
    POSITIVE LOGITS
     safety
    0.31
     Safety
    0.26
    Safety
    0.23
     environmental
    0.21
    å®īåħ¨
    0.21
    afety
    0.19
     safe
    0.18
     Environmental
    0.18
     environment
    0.17
     Environment
    0.17
    Activations Density 0.014%

    No Known Activations