© 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. 22719
    Prev
    Next
    INDEX
    Explanations

    previous and past

    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
     successors
    -0.11
     ******************************************************************************/\n
    -0.09
     AppModule
    -0.08
     nouvel
    -0.08
     NotImplemented
    -0.08
    _OW
    -0.07
    \<^
    -0.07
    /native
    -0.07
     newState
    -0.07
    sı
    -0.07
    POSITIVE LOGITS
     previous
    1.08
    previous
    0.80
     Previous
    0.79
    Previous
    0.75
    .previous
    0.57
    (previous
    0.57
    _previous
    0.56
    ä¹ĭåīį
    0.54
     earlier
    0.52
     önceki
    0.52
    Activations Density 0.338%

    No Known Activations