© 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. 11-RESID-POST-AA
    11. 36737
    Prev
    Next
    INDEX
    Explanations

    livelihood

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _go
    -0.07
     Recru
    -0.06
    (menu
    -0.06
     kapı
    -0.06
    說
    -0.06
     zwei
    -0.06
     hết
    -0.06
     hely
    -0.06
     gez
    -0.06
    -order
    -0.06
    POSITIVE LOGITS
     livelihood
    0.09
     riches
    0.07
     nab
    0.07
    ată
    0.06
    .Tasks
    0.06
    ітет
    0.06
    UST
    0.06
    $args
    0.06
    ари
    0.06
     Teeth
    0.06
    Activations Density 0.008%

    No Known Activations