© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58026
    Prev
    Next
    INDEX
    Explanations

    ological

    np_max-act · gemini-2.0-flash

    This neuron detects technical topology vocabulary, especially terms like “topological,” “space,” “compact,” and related modifiers (e.g. “locally,” “Hausdorff”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Founded
    -0.07
     شرکت
    -0.07
    .can
    -0.07
    +'
    -0.06
     filmmaker
    -0.06
     cycle
    -0.06
    .Sprintf
    -0.06
     printf
    -0.06
    .mean
    -0.06
    互联网
    -0.06
    POSITIVE LOGITS
    �蛛
    0.07
    -Assad
    0.06
     TODAY
    0.06
     autopsy
    0.06
    ))[
    0.06
    	duration
    0.06
    ريع
    0.06
     Sutton
    0.06
    -nine
    0.06
     ود
    0.06
    Activations Density 0.007%

    No Known Activations