© 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. 18681
    Prev
    Next
    INDEX
    Explanations

    promoting or creating solutions

    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
    561
    -0.10
     primitive
    -0.10
     threatened
    -0.10
     Tah
    -0.10
     recourse
    -0.09
    âĦĸâĦĸ
    -0.09
     Glover
    -0.09
     blackmail
    -0.09
    надлеж
    -0.09
     overhe
    -0.09
    POSITIVE LOGITS
     circum
    0.15
     potentially
    0.12
     accuracy
    0.12
     without
    0.11
    æ³
    0.11
     bypass
    0.10
     tam
    0.10
    -sensitive
    0.10
    èĤĸ
    0.10
     intellectual
    0.09
    Activations Density 0.158%

    No Known Activations