© 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. 11-RESID-POST-AA
    6. 27724
    Prev
    Next
    INDEX
    Explanations

    Modality

    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
    umes
    -0.07
    urances
    -0.06
    441
    -0.06
     existence
    -0.06
     agitation
    -0.06
    ITTLE
    -0.06
    >a
    -0.06
     مسائل
    -0.06
    悪
    -0.06
     calculations
    -0.06
    POSITIVE LOGITS
     chtě
    0.07
    พระ
    0.07
     příst
    0.07
     وهو
    0.07
     blaming
    0.06
    brero
    0.06
     لازم
    0.06
     the
    0.06
    /router
    0.06
    �
    0.06
    Activations Density 0.047%

    No Known Activations