© 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. 37444
    Prev
    Next
    INDEX
    Explanations

    genocide and mass killings

    np_max-act · gemini-2.0-flash
    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
    Grey
    -0.07
     khăn
    -0.07
    แก
    -0.06
    Tho
    -0.06
     quarterly
    -0.06
    ヘ
    -0.06
    英語
    -0.06
    Daily
    -0.06
     곧
    -0.06
     Dems
    -0.06
    POSITIVE LOGITS
    (Stream
    0.06
    scroll
    0.06
    ición
    0.06
     зн
    0.06
    _customize
    0.06
    lagen
    0.06
    910
    0.06
     кух
    0.06
    sm
    0.06
    ultipartFile
    0.05
    Activations Density 0.037%

    No Known Activations