© 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. 101223
    Prev
    Next
    INDEX
    Explanations

    was/is

    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
     temperament
    -0.07
    ">%
    -0.06
     sampled
    -0.06
    采购
    -0.05
    _SET
    -0.05
     goalkeeper
    -0.05
    _poly
    -0.05
     costs
    -0.05
    Hint
    -0.05
    }).
    -0.05
    POSITIVE LOGITS
    +-+-+-+-+-+-+-+-
    0.07
     OBJ
    0.07
    -refresh
    0.07
    -important
    0.07
    افظ
    0.07
    ารณ
    0.07
     व
    0.07
     Çev
    0.07
    quiet
    0.06
    CHKERRQ
    0.06
    Activations Density 0.048%

    No Known Activations