© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 45203
    Prev
    Next
    INDEX
    Explanations

    needs, happiness, relationships

    np_max-act · gemini-2.0-flash

    It detects tokens referring to character social/relationship state, needs, moods, and sexual or dating-related attributes.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    illian
    -0.07
    iedades
    -0.06
    idy
    -0.06
     embroidery
    -0.06
    ňování
    -0.06
     نیم
    -0.06
    ickém
    -0.06
    /no
    -0.06
     forg
    -0.06
     rak
    -0.06
    POSITIVE LOGITS
     UIF
    0.07
     each
    0.06
    .getModel
    0.06
    forc
    0.06
    ("_
    0.06
    一种
    0.06
    Machine
    0.06
     accusation
    0.06
    contra
    0.06
    智
    0.06
    Activations Density 0.075%

    No Known Activations