© 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. 19-RESID-POST-AA
    6. 118971
    Prev
    Next
    INDEX
    Explanations

    adult

    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
     anywhere
    -0.07
     shares
    -0.06
    	diff
    -0.06
     sq
    -0.06
     Dao
    -0.06
    LOTS
    -0.06
    Yaw
    -0.06
    pecific
    -0.06
    Legendary
    -0.06
     fisheries
    -0.06
    POSITIVE LOGITS
    تمع
    0.07
     знаю
    0.06
    ','');↵
    0.06
     elektron
    0.06
    ')"↵
    0.06
     manos
    0.06
    unci
    0.06
     مس
    0.06
     떠
    0.06
    促
    0.06
    Activations Density 0.006%

    No Known Activations