© 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. 21506
    Prev
    Next
    INDEX
    Explanations

    adult content

    np_max-act · gemini-2.0-flash

    requests or passages involving explicit sexual and pornographic scenarios, including coercive or taboo roleplay.

    oai_token-act-pair · gpt-5
    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
    Sig
    -0.06
     ")
↵
    -0.06
    ев
    -0.06
     المست
    -0.06
     ديگر
    -0.06
    lords
    -0.06
     дав
    -0.06
    CMP
    -0.06
    STDOUT
    -0.06
     cosm
    -0.06
    POSITIVE LOGITS
     headquarters
    0.06
    0.06
    .Cart
    0.06
    correo
    0.06
    %E
    0.06
    :";↵
    0.06
    Year
    0.06
    assic
    0.06
    inea
    0.06
     Henrik
    0.06
    Activations Density 0.262%

    No Known Activations