© 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. 14319
    Prev
    Next
    INDEX
    Explanations

    quart, quartos, equal, Selling, maths, mas, sempre

    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
     nuest
    -0.08
    @nate
    -0.08
    लà¤Ĺ
    -0.07
    jom
    -0.07
    ScrollIndicator
    -0.07
    -wsj
    -0.07
    _lng
    -0.07
    DisplayStyle
    -0.07
     Güven
    -0.07
    EMPLARY
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.07
     tempList
    0.07
    &#
    0.07
     Badge
    0.07
    MAND
    0.07
    wchar
    0.06
    «
    0.06
     onDataChange
    0.06
     defaultMessage
    0.06
     —;\n\n
    0.06
    Activations Density 0.099%

    No Known Activations