© 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 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. 57395
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the Portuguese cooking term for coating with flour (e.g. "enfarinhada"/"farinhada").

    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
     girdi
    -0.06
     Te
    -0.06
    usion
    -0.06
    monto
    -0.06
    -0.06
    iT
    -0.06
    ennis
    -0.06
    cff
    -0.06
    دانلود
    -0.06
    ่าว
    -0.06
    POSITIVE LOGITS
    며
    0.07
     EB
    0.07
    -schema
    0.07
     struggling
    0.07
     uży
    0.07
     ###
    0.07
     Комп
    0.07
     Serializable
    0.06
    .models
    0.06
     appearance
    0.06
    Activations Density 0.000%

    No Known Activations