© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 81405
    Prev
    Next
    INDEX
    Explanations

    code analysis tools

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्थल
    -0.08
     当
    -0.07
    랜드
    -0.06
    _opt
    -0.06
     설치
    -0.05
    tx
    -0.05
    abstractmethod
    -0.05
    ول
    -0.05
    .minecraftforge
    -0.05
    .pic
    -0.05
    POSITIVE LOGITS
    039
    0.07
     Ý
    0.07
     Serbian
    0.06
     Probe
    0.06
     bucks
    0.06
     Chapter
    0.06
    印
    0.06
     academic
    0.06
     Fortress
    0.06
     Scanner
    0.06
    Activations Density 0.038%

    No Known Activations