© 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. 58141
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on academic affiliation and address text (institution and location names in author/address blocks).

    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
     及
    -0.07
    owe
    -0.07
    .Select
    -0.07
     introduction
    -0.06
     columnIndex
    -0.06
    Regarding
    -0.06
     Раз
    -0.06
    "indices
    -0.06
     courtroom
    -0.06
     Scholarship
    -0.06
    POSITIVE LOGITS
     dispositivo
    0.06
    기업
    0.06
     акти
    0.06
     кислот
    0.06
    케이
    0.06
    犯罪
    0.06
     알아
    0.06
    _IMM
    0.06
    scala
    0.06
     систем
    0.06
    Activations Density 0.023%

    No Known Activations