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. 10281
    Prev
    Next
    INDEX
    Explanations

    Books

    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
     hardest
    -0.07
     выбра
    -0.07
    姉
    -0.07
    政
    -0.06
    	bar
    -0.06
     TypeScript
    -0.06
    18
    -0.06
    orpion
    -0.06
     voices
    -0.06
     bordered
    -0.06
    POSITIVE LOGITS
    _FOUND
    0.07
    /met
    0.07
    lovak
    0.06
    gan
    0.06
    Cong
    0.06
    .ct
    0.06
    :A
    0.05
    -liter
    0.05
    Prior
    0.05
     NGX
    0.05
    Activations Density 0.117%

    No Known Activations