© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 29703
    Prev
    Next
    INDEX
    Explanations

    ghana

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ajax
    -0.08
    *);↵↵
    -0.07
     Dur
    -0.07
     Je
    -0.07
     FACT
    -0.06
    _error
    -0.06
    capability
    -0.06
    																		
    -0.06
     mb
    -0.06
    团
    -0.06
    POSITIVE LOGITS
     danmark
    0.07
     Ghana
    0.07
    على
    0.06
     tracked
    0.06
     fatto
    0.06
     ทอง
    0.06
    Located
    0.06
     نگهداری
    0.06
     Bereich
    0.05
     exchanging
    0.05
    Activations Density 0.008%

    No Known Activations