© 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. 92291
    Prev
    Next
    INDEX
    Explanations

    gold

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of precious metals (e.g. “gold,” “silver,” etc.).

    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
     impatient
    -0.07
     otp
    -0.07
    олет
    -0.07
     weit
    -0.07
    (auto
    -0.06
    _ACT
    -0.06
     Tep
    -0.06
    Dem
    -0.06
    갈
    -0.06
     слов
    -0.06
    POSITIVE LOGITS
     gold
    0.08
    -resource
    0.08
    __.
    0.07
    368
    0.07
     Christopher
    0.07
    krit
    0.07
     Hanging
    0.07
     options
    0.06
     steak
    0.06
    cerer
    0.06
    Activations Density 0.015%

    No Known Activations