© 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. 36742
    Prev
    Next
    INDEX
    Explanations

    -

    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
    atic
    -0.07
    افت
    -0.06
    _MAT
    -0.06
     увелич
    -0.06
     initData
    -0.06
    цій
    -0.06
    cla
    -0.06
    ήλ
    -0.06
    zes
    -0.06
     Vendor
    -0.06
    POSITIVE LOGITS
     Suddenly
    0.06
     因
    0.06
     floods
    0.06
     campground
    0.06
    (fm
    0.06
     Gradient
    0.06
     Neighborhood
    0.06
     Savings
    0.06
    ,-
    0.06
    Billing
    0.06
    Activations Density 0.004%

    No Known Activations