Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9718
    Prev
    Next
    INDEX
    Explanations

    bill

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entre
    -0.07
     ध
    -0.07
    ......
    -0.06
     попыт
    -0.06
    getRepository
    -0.06
    _drag
    -0.06
     север
    -0.06
     теат
    -0.06
     eros
    -0.06
     recess
    -0.06
    POSITIVE LOGITS
     bill
    0.13
     Bill
    0.10
    Bill
    0.09
     bills
    0.09
     bil
    0.08
     BILL
    0.08
    ,_
    0.07
     Bills
    0.07
     Biblical
    0.07
     BAB
    0.07
    Activations Density 0.010%

    No Known Activations