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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 35201
    Prev
    Next
    INDEX
    Explanations

    FileReader

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Imports
    -0.07
    -sn
    -0.07
    ­tion
    -0.07
    _boolean
    -0.07
    름
    -0.06
    -validation
    -0.06
    .author
    -0.06
     створення
    -0.06
     races
    -0.06
     forests
    -0.06
    POSITIVE LOGITS
    endereco
    0.07
    tplib
    0.06
     Cad
    0.06
     Behavioral
    0.06
    igner
    0.06
    ंक
    0.06
     deter
    0.06
     permalink
    0.06
     Cristiano
    0.06
     interpersonal
    0.06
    Activations Density 0.002%

    No Known Activations