© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74738
    Prev
    Next
    INDEX
    Explanations

    'é

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to accented characters (letters with diacritics) in the text.

    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
     �
    -0.08
    Peak
    -0.07
    عان
    -0.07
     Carn
    -0.07
    parm
    -0.07
    ㅎ
    -0.07
     '+
    -0.07
    форм
    -0.07
     breastfeeding
    -0.07
    holds
    -0.07
    POSITIVE LOGITS
     é
    0.08
    .setEditable
    0.07
    'é
    0.07
    462
    0.07
     extingu
    0.07
     seleccion
    0.07
    ’é
    0.07
     examination
    0.06
    148
    0.06
     Spect
    0.06
    Activations Density 0.048%

    No Known Activations