© 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. 38557
    Prev
    Next
    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash

    The neuron responds to explicit, first‐person declarations of emotional closeness or affection—especially “I love you”–type statements.

    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
    epad
    -0.06
    Nama
    -0.06
     backtrack
    -0.06
    Universal
    -0.06
    (Category
    -0.06
     Voices
    -0.06
     taky
    -0.06
     superheroes
    -0.06
     showdown
    -0.06
     Anime
    -0.06
    POSITIVE LOGITS
    quist
    0.07
     riv
    0.06
     Splash
    0.06
    -lived
    0.06
     splitter
    0.06
    993
    0.06
    legg
    0.06
     priv
    0.06
     homepage
    0.06
    .React
    0.06
    Activations Density 0.048%

    No Known Activations