© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109771
    Prev
    Next
    INDEX
    Explanations

    Real estate leasing

    np_max-act · gemini-2.0-flash

    The neuron activates on real‐estate property descriptors—especially when noting industrial/commercial project sizes (e.g. square‐footage measurements).

    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
    -0.07
     caz
    -0.06
    IBLE
    -0.06
     snippet
    -0.06
    ScrollBar
    -0.06
     shipments
    -0.06
     Sandra
    -0.06
    _capacity
    -0.06
     introduces
    -0.06
     IndexPath
    -0.06
    POSITIVE LOGITS
     kam
    0.07
     Cobb
    0.06
     nich
    0.06
    خاب
    0.06
    。',↵
    0.06
     Tehran
    0.06
     prost
    0.06
     gr
    0.06
    _pag
    0.06
    .Method
    0.06
    Activations Density 0.017%

    No Known Activations