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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85184
    Prev
    Next
    INDEX
    Explanations

    superclass

    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
     Тут
    -0.07
    shan
    -0.07
     MATRIX
    -0.06
    .double
    -0.06
    lg
    -0.06
    _PRI
    -0.06
     programme
    -0.06
    rea
    -0.06
    ven
    -0.06
    (progress
    -0.06
    POSITIVE LOGITS
     weakening
    0.06
    ernals
    0.06
     �
    0.06
     Abyss
    0.06
    SENSOR
    0.06
    审
    0.06
    migration
    0.06
    还是
    0.06
    MASConstraintMaker
    0.06
     CircularProgressIndicator
    0.06
    Activations Density 0.014%

    No Known Activations