© 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. 7673
    Prev
    Next
    INDEX
    Explanations

    Buying and products

    np_max-act · gemini-2.0-flash

    The neuron flags terms having to do with consumption and consumer products (e.g. “consumption,” “products,” “use,” “sustainable”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     tomatoes
    -0.07
     обра
    -0.07
    行为
    -0.06
    _fx
    -0.06
     المؤ
    -0.06
    育
    -0.06
    (Console
    -0.06
    yes
    -0.06
     Mühendis
    -0.06
    objs
    -0.06
    POSITIVE LOGITS
     selectable
    0.07
     fuck
    0.07
     centrally
    0.07
     Dot
    0.06
     आप
    0.06
     achieves
    0.06
     disappointing
    0.06
    �
    0.06
     (--
    0.06
    VERTISEMENT
    0.06
    Activations Density 0.048%

    No Known Activations