© 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. 21357
    Prev
    Next
    INDEX
    Explanations

    deep

    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_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
     Kyle
    -0.08
     barn
    -0.07
     Auschwitz
    -0.07
    _station
    -0.07
     learning
    -0.07
    灵
    -0.07
     ایشان
    -0.07
    IMP
    -0.07
     руках
    -0.07
     Ahmad
    -0.07
    POSITIVE LOGITS
    Include
    0.06
    不同的
    0.06
    _trampoline
    0.06
    ?,↵
    0.06
    ('--
    0.06
    _ip
    0.06
    $error
    0.05
    "',
    0.05
    ('-',
    0.05
     dul
    0.05
    Activations Density 0.004%

    No Known Activations