© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8576
    Prev
    Next
    INDEX
    Explanations

    sentence structure or classification

    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
    /preferences
    -0.10
    ëĶ
    -0.09
    .IsNullOr
    -0.08
     Deniz
    -0.08
     Nass
    -0.08
    ventus
    -0.08
    edException
    -0.08
    ucch
    -0.08
    âĪı
    -0.08
    reb
    -0.08
    POSITIVE LOGITS
    (s
    0.29
    (es
    0.15
    [s
    0.15
    ency
    0.10
    (en
    0.10
     Griffin
    0.10
    {s
    0.09
     specifically
    0.09
    pecific
    0.09
    ame
    0.09
    Activations Density 0.018%

    No Known Activations