© 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. 11-RESID-POST-AA
    11. 47941
    Prev
    Next
    INDEX
    Explanations

    condition

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _dependency
    -0.07
    _CONSTANT
    -0.06
     เก
    -0.06
    Cors
    -0.06
    ===========
    -0.06
    Metadata
    -0.06
    SPA
    -0.06
     grandparents
    -0.06
    yaml
    -0.06
    _estimate
    -0.06
    POSITIVE LOGITS
     complain
    0.08
     guarda
    0.07
     overhaul
    0.07
    gment
    0.07
    (Document
    0.07
     urging
    0.07
     deterior
    0.07
     society
    0.07
     distressed
    0.07
     infusion
    0.07
    Activations Density 0.017%

    No Known Activations