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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6984
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on the standard “competed in the [event] at the [year] Summer/Winter Olympics” phrasing that describes an athlete’s Olympic participation.

    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
     thư
    -0.07
     Coat
    -0.07
    {|
    -0.06
     леж
    -0.06
    licity
    -0.06
     SW
    -0.06
    кут
    -0.06
    Ax
    -0.06
    .accounts
    -0.06
    аш
    -0.06
    POSITIVE LOGITS
    /problem
    0.07
    Crystal
    0.07
     panda
    0.06
     Michigan
    0.06
    Animating
    0.06
    orc
    0.06
    ристи
    0.06
    submitted
    0.06
    .phase
    0.06
     مبانی
    0.06
    Activations Density 0.003%

    No Known Activations