© 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. 47299
    Prev
    Next
    INDEX
    Explanations

    goal of, score of, wants, refers to, better to, rather than

    np_acts-logits-general · gemini-2.5-flash-lite

    formal, instructional, or procedural language typical of explanatory or educational content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    ãĥ¼ãĥ¼
    -0.10
    ï½ŀï½ŀ
    -0.09
    ãĢģãĢģ
    -0.09
     ragaz
    -0.09
    mobx
    -0.08
    .synthetic
    -0.08
     ún
    -0.08
    .Dependency
    -0.07
    ô
    -0.07
     modne
    -0.07
    POSITIVE LOGITS
     ÄijÃłi
    0.08
     phúc
    0.08
    _inches
    0.08
    .TestCase
    0.08
    '
    0.08
     Jong
    0.07
    (||
    0.07
    .getSystemService
    0.07
    ailles
    0.07
     xsi
    0.07
    Activations Density 5.124%

    No Known Activations