© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68589
    Prev
    Next
    INDEX
    Explanations

    Names/locations

    np_max-act · gemini-2.0-flash

    This neuron fires on personal names, especially multi‐part (e.g., first + last) proper names.

    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
     금
    -0.07
    (memory
    -0.07
     Joey
    -0.07
     ties
    -0.06
    imos
    -0.06
    ey
    -0.06
     signer
    -0.06
    iParam
    -0.06
    (file
    -0.06
     ngọt
    -0.06
    POSITIVE LOGITS
    bír
    0.07
    ulations
    0.06
     EXTRA
    0.06
    RACT
    0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
     LPARAM
    0.06
    .qml
    0.06
     Paths
    0.06
     تبلی
    0.06
    フェ
    0.06
    Activations Density 0.034%

    No Known Activations