© 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. 26878
    Prev
    Next
    INDEX
    Explanations

    �

    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
    -b
    -0.07
     bac
    -0.07
    OMB
    -0.07
    _BLE
    -0.06
    _BO
    -0.06
    ;b
    -0.06
    setBackground
    -0.06
    Б
    -0.06
     bg
    -0.06
    blob
    -0.06
    POSITIVE LOGITS
     Takım
    0.08
     Тер
    0.07
    UInt
    0.07
     nationally
    0.07
    OrderId
    0.07
     atrocities
    0.07
    Ul
    0.07
    _TEST
    0.07
    ustom
    0.07
    	connect
    0.06
    Activations Density 3.325%

    No Known Activations