Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 176
    Prev
    Next
    INDEX
    Explanations

    factory

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot references to the automotive industry—car brands, car museums, factories, and manufacturing.

    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
    채
    -0.07
    ैच
    -0.07
     dro
    -0.06
     unearth
    -0.06
    Emp
    -0.06
     Rew
    -0.06
    στό
    -0.06
     SUN
    -0.06
    03
    -0.06
     wisely
    -0.06
    POSITIVE LOGITS
     날짜
    0.07
    ころ
    0.07
    iguous
    0.06
    cams
    0.06
    //
    0.06
     birbir
    0.06
     обязатель
    0.06
     NEGLIGENCE
    0.06
     پایان
    0.06
    .contentMode
    0.06
    Activations Density 0.032%

    No Known Activations