© 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. 21431
    Prev
    Next
    INDEX
    Explanations

    high-stakes situations

    np_max-act · gemini-2.0-flash

    sentences describing imminent physical harm or violent scenarios and moral dilemmas about killing (e.g., trolley-problem style situations).

    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
     observations
    -0.08
     stom
    -0.08
    eyle
    -0.07
     pest
    -0.07
     veil
    -0.07
     infectious
    -0.06
    .refresh
    -0.06
     ``
    -0.06
     knives
    -0.06
     hik
    -0.06
    POSITIVE LOGITS
    .arr
    0.07
    郎
    0.07
    >e
    0.07
    ))+
    0.06
    ，无
    0.06
     ทอง
    0.06
     signed
    0.06
    ี.
    0.06
    J
    0.06
     indicated
    0.06
    Activations Density 0.141%

    No Known Activations