© 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. 28816
    Prev
    Next
    INDEX
    Explanations

    Blog posts

    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
    	session
    -0.07
    ervices
    -0.07
     Capability
    -0.07
    /**<
    -0.06
    DISPLAY
    -0.06
    spark
    -0.06
    าตรฐาน
    -0.06
    рупп
    -0.06
    Officials
    -0.06
     vanity
    -0.06
    POSITIVE LOGITS
    яття
    0.07
    (PRO
    0.06
    setMessage
    0.06
     amendments
    0.06
    gresql
    0.06
     приб
    0.06
     Strawberry
    0.06
     ноября
    0.06
    _secondary
    0.06
    esse
    0.06
    Activations Density 0.024%

    No Known Activations