© 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. 24995
    Prev
    Next
    INDEX
    Explanations

    drug being tested

    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
     recognised
    -0.09
     realised
    -0.09
    iston
    -0.09
    olls
    -0.08
     published
    -0.08
     initialised
    -0.08
     lep
    -0.08
    055
    -0.08
     adm
    -0.08
    -0.08
    POSITIVE LOGITS
     studied
    0.26
     ÙħÙĪرد
    0.24
     study
    0.23
    stud
    0.23
     tested
    0.22
     target
    0.22
    tested
    0.22
     investigated
    0.21
     изÑĥÑĩ
    0.20
    Reviewed
    0.19
    Activations Density 0.270%

    No Known Activations