© 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
    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. 9509
    Prev
    Next
    INDEX
    Explanations

    Seth

    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
     Vous
    -0.07
    ungalow
    -0.07
     дом
    -0.06
     Ми
    -0.06
    "})
    -0.06
     pie
    -0.06
    라고
    -0.06
    $args
    -0.06
     ду
    -0.06
    から
    -0.06
    POSITIVE LOGITS
    (parseFloat
    0.06
     apparent
    0.06
    arching
    0.06
    اسطة
    0.06
    ForResource
    0.06
    .fetch
    0.06
     Veranst
    0.06
     다양
    0.06
     reactive
    0.06
    -held
    0.06
    Activations Density 0.001%

    No Known Activations