© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 52196
    Prev
    Next
    INDEX
    Explanations

    Up

    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
    ды
    -0.06
     outrage
    -0.06
     resorts
    -0.06
     المن
    -0.06
    -door
    -0.06
     alcuni
    -0.06
    ้บร
    -0.06
    ावन
    -0.06
    ┘
    -0.06
    уют
    -0.06
    POSITIVE LOGITS
     prevention
    0.07
     precisely
    0.07
     Prevention
    0.06
    Left
    0.06
    呼
    0.06
    ,event
    0.06
    ieber
    0.06
     SS
    0.06
    (panel
    0.06
    CSS
    0.06
    Activations Density 0.000%

    No Known Activations