© 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. 58423
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron fires on Portuguese nutritional‐content descriptions—especially “rico em …” or similar “rich in …” phrases.

    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
    *time
    -0.08
    /mainwindow
    -0.07
    (last
    -0.07
    _paper
    -0.07
    =obj
    -0.07
    _dialog
    -0.07
    (Connection
    -0.07
    =url
    -0.07
    AndPassword
    -0.07
    _PERSON
    -0.07
    POSITIVE LOGITS
    集合
    0.06
     ky
    0.06
    WSC
    0.06
    SG
    0.06
     üz
    0.06
    άς
    0.06
    CENT
    0.05
     More
    0.05
     Binder
    0.05
     आस
    0.05
    Activations Density 0.021%

    No Known Activations