© 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. 23898
    Prev
    Next
    INDEX
    Explanations

    content style description

    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
     identical
    -0.09
    juan
    -0.08
     Ferd
    -0.08
    yme
    -0.08
     spelling
    -0.08
    pread
    -0.08
     ç¤
    -0.08
     whe
    -0.08
     تÙĤÙĪ
    -0.08
     eup
    -0.08
    POSITIVE LOGITS
     style
    0.29
    style
    0.23
     Style
    0.22
     estilo
    0.22
     styles
    0.21
    (style
    0.21
    -style
    0.20
     STYLE
    0.20
    _style
    0.20
    Style
    0.20
    Activations Density 0.251%

    No Known Activations