© 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. 56196
    Prev
    Next
    INDEX
    Explanations

    attributes are used to define something

    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
     MethodInfo
    -0.11
    AccessorType
    -0.11
    comb
    -0.10
    [sizeof
    -0.10
    auf
    -0.10
    uuid
    -0.09
    leh
    -0.09
     Abrams
    -0.09
    RSS
    -0.09
    URLException
    -0.09
    POSITIVE LOGITS
     properties
    0.15
     key
    0.15
     att
    0.14
     pairs
    0.14
     property
    0.14
     attribute
    0.13
     attributes
    0.13
    éĶ®
    0.13
    NameValuePair
    0.12
    Pairs
    0.12
    Activations Density 0.131%

    No Known Activations