© 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. 56365
    Prev
    Next
    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash

    functions related to data manipulation in spreadsheets.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects Spanish terms referring to table rows (e.g. “filas”).

    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
     tv
    -0.08
     flies
    -0.07
     dij
    -0.07
    els
    -0.06
    -0.06
     connected
    -0.06
     speaks
    -0.06
     leaking
    -0.06
     Лени
    -0.06
     ремонт
    -0.06
    POSITIVE LOGITS
     *)↵↵
    0.08
    PREC
    0.07
    .contentView
    0.06
     Mavericks
    0.06
    .pageY
    0.06
     NEW
    0.06
    ."↵↵↵
    0.06
    >");
↵
    0.06
    _rows
    0.06
     мистецт
    0.06
    Activations Density 0.020%

    No Known Activations