© 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. 11-RESID-POST-AA
    6. 18461
    Prev
    Next
    INDEX
    Explanations

    True

    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
     RCC
    -0.06
     могли
    -0.06
    Your
    -0.06
     paints
    -0.06
     sagen
    -0.06
    �
    -0.06
    ничес
    -0.06
     proyecto
    -0.06
     �
    -0.06
     Archive
    -0.06
    POSITIVE LOGITS
    BOT
    0.07
    /$
    0.06
    produ
    0.06
    -toolbar
    0.06
    Exception
    0.06
    (('
    0.06
    (ib
    0.06
    getCell
    0.06
    (MSG
    0.06
    -python
    0.06
    Activations Density 0.002%

    No Known Activations