© 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. 44533
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
    43
    -0.07
    .From
    -0.07
    řízení
    -0.07
    _BY
    -0.07
     cx
    -0.06
    ์ฟ
    -0.06
    44
    -0.06
    285
    -0.06
     If
    -0.06
     converged
    -0.06
    POSITIVE LOGITS
     ihren
    0.11
     nuestro
    0.10
     ihrem
    0.09
     ihre
    0.09
     свои
    0.09
     leur
    0.09
     leurs
    0.09
     suo
    0.08
     seinem
    0.08
     seine
    0.08
    Activations Density 0.058%

    No Known Activations