© 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. 400
    Prev
    Next
    INDEX
    Explanations

    many items

    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
     meille
    -0.09
    <|begin_of_text|>
    -0.08
     ydk
    -0.08
    eya
    -0.08
     kostenlose
    -0.08
     nackte
    -0.08
    \Dependency
    -0.08
    Ỽm
    -0.08
    ä¹ħ
    -0.08
    ÄĽt
    -0.08
    POSITIVE LOGITS
     several
    0.51
     many
    0.38
     Several
    0.35
    Several
    0.32
    veral
    0.28
     various
    0.28
     numerous
    0.28
     beberapa
    0.27
    many
    0.27
    åĩłä¸ª
    0.27
    Activations Density 0.828%

    No Known Activations