© 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. 20187
    Prev
    Next
    INDEX
    Explanations

    user turns

    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
     kontakte
    -0.09
     Olsen
    -0.09
    ModelError
    -0.08
    emen
    -0.08
    opup
    -0.08
    alon
    -0.08
     Mens
    -0.08
    culate
    -0.08
     اÙĦØŃر
    -0.08
    avar
    -0.08
    POSITIVE LOGITS
    erator
    0.09
    hma
    0.09
    chia
    0.09
     Briggs
    0.09
     launder
    0.08
    ile
    0.08
     McKenzie
    0.08
     Bounty
    0.08
    asaki
    0.08
    alyzer
    0.08
    Activations Density 0.003%

    No Known Activations