© 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. 12636
    Prev
    Next
    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    This neuron activates on words about purchasing or spending money (e.g., get, pay, cost, buy).

    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
    teenth
    -0.08
    енная
    -0.08
    ila
    -0.06
    .CompilerServices
    -0.06
     Picture
    -0.06
     tou
    -0.06
    療
    -0.06
    ============↵
    -0.06
     Hydraulic
    -0.06
     shuffled
    -0.06
    POSITIVE LOGITS
     퍼
    0.07
     컨
    0.06
     rulings
    0.06
     neut
    0.06
    rox
    0.06
     peculiar
    0.06
     CAD
    0.06
    реди
    0.06
    ;

↵
    0.06
    aksi
    0.06
    Activations Density 0.070%

    No Known Activations