© 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. 44605
    Prev
    Next
    INDEX
    Explanations

    this followed by modal verbs

    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
    oins
    -0.09
    NotAllowed
    -0.09
    ÐķС
    -0.09
    ulia
    -0.08
    .GroupLayout
    -0.08
     Clair
    -0.08
    requires
    -0.08
     )\n\n\n\n\n\n\n\n
    -0.08
    riday
    -0.08
     requires
    -0.08
    POSITIVE LOGITS
     could
    0.42
    could
    0.36
     might
    0.36
     Could
    0.32
    Could
    0.32
    might
    0.30
     bisa
    0.29
     könnte
    0.27
     podrÃŃa
    0.26
     pourrait
    0.26
    Activations Density 0.152%

    No Known Activations