© 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. 64961
    Prev
    Next
    INDEX
    Explanations

    and

    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
    .scale
    -0.06
     comfortably
    -0.06
    .rank
    -0.06
     دولتی
    -0.06
    Strategy
    -0.06
    اید
    -0.06
    _layers
    -0.06
    _PROJECT
    -0.06
    HZ
    -0.06
     بهبود
    -0.06
    POSITIVE LOGITS
     flexGrow
    0.07
     компон
    0.07
    member
    0.07
    /hash
    0.06
     hodnot
    0.06
     Vend
    0.06
    andas
    0.06
    >H
    0.06
    imento
    0.06
     horrend
    0.06
    Activations Density 0.144%

    No Known Activations