© 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. 24482
    Prev
    Next
    INDEX
    Explanations

    Blue landscapeA dogwith its* Buildingnation'sthis extensionyour answercat:Debt secondary

    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
     TMPro
    -0.08
    --,
    -0.08
     resemblance
    -0.07
     огÑĢа
    -0.07
     lesbi
    -0.07
    кеÑĤ
    -0.07
    \tTokenName
    -0.07
    ä»ķ
    -0.07
    )./
    -0.07
     -------
    -0.07
    POSITIVE LOGITS
     endregion
    0.11
     category
    0.10
     adlı
    0.10
     option
    0.09
     item
    0.09
     tématu
    0.09
    longleftrightarrow
    0.08
    ä¾ĭ
    0.08
    ovit
    0.08
    _equalTo
    0.08
    Activations Density 0.311%

    No Known Activations