© 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. 15-RESID-POST-AA
    11. 18618
    Prev
    Next
    INDEX
    Explanations

    author

    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
    Negative Logits
     Hud
    -0.07
     cocaine
    -0.06
    .classes
    -0.06
    Diamond
    -0.06
    íc
    -0.06
     productList
    -0.06
     за
    -0.06
    atím
    -0.06
    ihu
    -0.06
    :def
    -0.06
    POSITIVE LOGITS
     TRAIN
    0.07
    /art
    0.06
     خ
    0.06
     rif
    0.06
     sucht
    0.06
    _cash
    0.06
     dissolve
    0.06
     geniş
    0.06
    vál
    0.06
    illum
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.