© 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. 45660
    Prev
    Next
    INDEX
    Explanations

    's

    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
    ょう
    -0.07
    .When
    -0.06
    「あ
    -0.06
     worsening
    -0.06
    ”—
    -0.06
     اجرای
    -0.06
     chemical
    -0.06
    ,"
    -0.06
    ）の
    -0.06
    )/
    -0.06
    POSITIVE LOGITS
    ραν
    0.07
    unic
    0.07
     backwards
    0.07
    odate
    0.07
     judgement
    0.07
    GIT
    0.06
     seperate
    0.06
    cloud
    0.06
    islav
    0.06
    oge
    0.06
    Activations Density 1.319%

    No Known Activations