© 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. 28543
    Prev
    Next
    INDEX
    Explanations

    human assistant and engineering

    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
    елик
    -0.09
    858
    -0.09
     Corinth
    -0.09
     Moose
    -0.09
    lio
    -0.09
    微软éĽħé»ij
    -0.09
    bear
    -0.09
     unk
    -0.09
     Marble
    -0.09
     mant
    -0.08
    POSITIVE LOGITS
     Taylor
    0.25
    Taylor
    0.22
    aylor
    0.17
     assembly
    0.16
     Assembly
    0.15
     Tay
    0.15
     worker
    0.14
     Scientific
    0.14
     factory
    0.13
     piece
    0.13
    Activations Density 0.047%

    No Known Activations