© 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. 29274
    Prev
    Next
    INDEX
    Explanations

    make sure

    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
    assy
    -0.10
    ä½ľ
    -0.09
    ses
    -0.09
    urdu
    -0.09
    astle
    -0.08
    zzo
    -0.08
    .scalablytyped
    -0.08
     making
    -0.08
     Hass
    -0.08
    _STA
    -0.08
    POSITIVE LOGITS
     sure
    0.64
    sure
    0.41
     Sure
    0.39
    Sure
    0.35
    SURE
    0.25
     sicher
    0.22
     chắc
    0.21
     sûr
    0.20
     ensure
    0.19
     sû
    0.19
    Activations Density 0.024%

    No Known Activations