© 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. 19-RESID-POST-AA
    11. 54117
    Prev
    Next
    INDEX
    Explanations

    Italian opera

    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
     그냥
    -0.06
    dling
    -0.06
     returnType
    -0.06
     yanı
    -0.06
    DEFINE
    -0.06
    mond
    -0.06
     :
    -0.06
     spectrum
    -0.06
    Seven
    -0.06
     Amend
    -0.06
    POSITIVE LOGITS
    ヶ月
    0.07
    _flash
    0.06
     منابع
    0.06
     بش
    0.06
    icaret
    0.06
    nome
    0.06
     perman
    0.06
    faith
    0.06
    _tipo
    0.06
     aument
    0.06
    Activations Density 0.007%

    No Known Activations