© 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. 22763
    Prev
    Next
    INDEX
    Explanations

    verb or preposition followed by noun phrase

    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
     interf
    -0.09
     neither
    -0.08
    var
    -0.08
     Bret
    -0.08
    ï¸ı
    -0.08
    older
    -0.08
    vido
    -0.08
    other
    -0.08
    anye
    -0.08
     certain
    -0.08
    POSITIVE LOGITS
     history
    0.12
     tradition
    0.12
    leon
    0.09
     the
    0.09
     suburb
    0.09
     reality
    0.09
     mañana
    0.09
    atown
    0.09
    neider
    0.09
     History
    0.09
    Activations Density 0.150%

    No Known Activations