© 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. 19-RESID-POST-AA
    11. 83922
    Prev
    Next
    INDEX
    Explanations

    Sp

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kepada
    -0.06
     preempt
    -0.06
     purpos
    -0.06
    ("================
    -0.06
     predetermined
    -0.06
    leniyor
    -0.06
     chết
    -0.06
    niejs
    -0.06
    ileceği
    -0.06
     lượt
    -0.06
    POSITIVE LOGITS
    CV
    0.08
    SP
    0.07
     sp
    0.07
    ожет
    0.07
     Sp
    0.07
    ANGES
    0.07
    SF
    0.07
    .IP
    0.07
    ='
    0.07
    sp
    0.07
    Activations Density 0.021%

    No Known Activations