© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35995
    Prev
    Next
    INDEX
    Explanations

    desenvolvimento / desenvolver

    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
    ioni
    -0.10
     Cable
    -0.09
    Latch
    -0.09
    orch
    -0.09
     Mast
    -0.09
     cable
    -0.09
    .uni
    -0.09
    acoes
    -0.09
    allas
    -0.09
    enso
    -0.09
    POSITIVE LOGITS
    olvimento
    0.23
    olved
    0.16
    PMENT
    0.13
    oment
    0.13
    olver
    0.13
    olve
    0.12
    lop
    0.12
    implify
    0.12
    azo
    0.12
    artment
    0.12
    Activations Density 0.024%

    No Known Activations