© 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. 13379
    Prev
    Next
    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash

    This neuron highlights mentions of fees and charges (especially shipping, return‐shipping, and restocking costs).

    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
    _HALF
    -0.07
     WAR
    -0.06
     student
    -0.06
    $j
    -0.06
    ERAL
    -0.06
     Patients
    -0.06
    Titulo
    -0.06
     Jupiter
    -0.06
    =',
    -0.06
     富
    -0.06
    POSITIVE LOGITS
     홍
    0.07
     Charlottesville
    0.07
    ird
    0.06
     dirección
    0.06
     ﺍ
    0.06
    νονται
    0.06
    вей
    0.06
    nger
    0.06
     Dul
    0.06
     artık
    0.06
    Activations Density 0.005%

    No Known Activations