© 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. 64742
    Prev
    Next
    INDEX
    Explanations

    superlatives

    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
    _message
    -0.07
    -filter
    -0.07
     USHORT
    -0.06
     ros
    -0.06
    _upgrade
    -0.06
    _SEARCH
    -0.06
    ’den
    -0.06
     bitterness
    -0.06
    Impossible
    -0.06
    printf
    -0.06
    POSITIVE LOGITS
    J
    0.07
    _cast
    0.06
     J
    0.06
     stab
    0.06
    ennessee
    0.06
     انجمن
    0.05
    鐘
    0.05
     اف
    0.05
    Apollo
    0.05
    册
    0.05
    Activations Density 0.037%

    No Known Activations