© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20306
    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     سبب
    -0.07
    	gen
    -0.06
     المد
    -0.06
     голови
    -0.06
     زمین
    -0.06
    ổi
    -0.06
     Lung
    -0.06
    _by
    -0.06
     دستی
    -0.06
     Libert
    -0.06
    POSITIVE LOGITS
    vably
    0.07
    apons
    0.07
     Multimedia
    0.06
    наруж
    0.06
     ℝ
    0.06
    -os
    0.06
    _pd
    0.06
    ativa
    0.06
    ycl
    0.06
    sko
    0.06
    Activations Density 0.004%

    No Known Activations