© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 127861
    Prev
    Next
    INDEX
    Explanations

    Narratives

    np_max-act · gemini-2.0-flash

    mentions of female characters or feminine third-person references (words like she, her, woman, saleswoman, bartender).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     спортив
    -0.07
    cliente
    -0.07
    ksiyon
    -0.06
    .Setup
    -0.06
     towers
    -0.06
    Portrait
    -0.06
    ذیر
    -0.06
     首页
    -0.06
     addItem
    -0.06
    .onResume
    -0.06
    POSITIVE LOGITS
     annotate
    0.06
     Desert
    0.06
     displaying
    0.06
     economical
    0.06
    “A
    0.06
     ιστο
    0.06
    ướ
    0.06
    amount
    0.06
    atcher
    0.06
    ázd
    0.05
    Activations Density 0.069%

    No Known Activations