© 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. 43570
    Prev
    Next
    INDEX
    Explanations

    ple- words

    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
    t
    -0.13
    red
    -0.11
    n
    -0.10
    na
    -0.10
    rys
    -0.10
    ses
    -0.10
    rior
    -0.10
    oke
    -0.10
    ingham
    -0.10
     Copp
    -0.10
    POSITIVE LOGITS
     Ple
    0.21
     ple
    0.20
    ple
    0.18
    ural
    0.15
    iminary
    0.14
    PLE
    0.13
    URAL
    0.12
     guilty
    0.12
    ople
    0.12
     pleasing
    0.11
    Activations Density 0.022%

    No Known Activations