© 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. 8248
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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
    noch
    -0.10
    #
    -0.10
     ë¨
    -0.10
    aga
    -0.10
     zwar
    -0.08
    orz
    -0.08
    upp
    -0.08
    âĨĴâĨĴ
    -0.08
     ë¸
    -0.08
    ccione
    -0.08
    POSITIVE LOGITS
    ters
    0.14
     ultimately
    0.13
     couldn
    0.12
    ler
    0.12
     instead
    0.11
     soon
    0.11
    ting
    0.11
    ts
    0.10
    ı
    0.10
     efforts
    0.10
    Activations Density 0.014%

    No Known Activations